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

    Neuronpedia

    INDEX
    Explanations

    code structure and test case definitions in programming contexts

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

    New Castle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    posedge
    -0.71
    copg
    -0.65
    StoryboardSegue
    -0.61
    MethodManager
    -0.60
     FetchType
    -0.60
    WriteTagHelper
    -0.57
    astify
    -0.55
    enschaften
    -0.55
    antMatchers
    -0.55
     fantasy
    -0.54
    POSITIVE LOGITS
     Comprometido
    0.39
    Còn
    0.36
     establece
    0.32
    věr
    0.32
     Inscrivez
    0.32
    ająca
    0.32
     demandent
    0.31
     Cliquez
    0.31
     кіль
    0.31
     esfuer
    0.30
    Act Density 0.000%

    No Known Activations