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

    Neuronpedia

    INDEX
    Explanations

    relationships characterized by emotional conflict and uncertainty

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

    something is wrong or not working

    np_acts-logits-general · gemini-2.0-flash

    not working as expected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.84
     nahilalakip
    -0.76
    LookAnd
    -0.71
    PerformLayout
    -0.66
    awaiter
    -0.62
     pinulongan
    -0.62
     Мексичка
    -0.61
    InstrumentedTest
    -0.61
    ")){
    -0.61
    ----</
    -0.60
    POSITIVE LOGITS
     coz
    0.58
     hanged
    0.58
     thingy
    0.53
     convenable
    0.51
     chale
    0.51
     somehow
    0.50
     quitted
    0.50
    soever
    0.49
    logues
    0.49
     really
    0.48
    Act Density 0.444%

    No Known Activations