Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns and expressions indicating opinion or belief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text following conjunctions or discourse markers

    np_acts-logits-general · gemini-2.0-flash

    results or research papers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Географиясе
    -0.40
    曖昧さ回避
    -0.40
     Fleetwood
    -0.38
    าร
    -0.38
     robustness
    -0.37
     MULTI
    -0.37
     Hewitt
    -0.36
     mem
    -0.36
     tem
    -0.36
     manual
    -0.36
    POSITIVE LOGITS
    EndProject
    0.53
    CloseOperation
    0.48
    पया
    0.47
    StoryboardSegue
    0.44
    CodeAttribute
    0.43
    RegressionTest
    0.43
     typelib
    0.42
     Photocase
    0.41
    دانشنامهٔ
    0.41
     inilah
    0.40
    Act Density 0.496%

    No Known Activations