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

    Neuronpedia

    INDEX
    Explanations

    contradictory or contrasting phrases

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

    but she"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __':
    -0.68
    OGND
    -0.68
     snippetHide
    -0.64
    oredCriteria
    -0.60
    Tikang
    -0.58
    ThroughAttribute
    -0.56
    __":
    -0.55
    -0.54
    complexContent
    -0.54
     autorytatywna
    -0.53
    POSITIVE LOGITS
    MessageTagHelper
    0.40
    CloseOperation
    0.36
    CharStream
    0.33
    Sec
    0.33
    addGroup
    0.32
     bet
    0.32
    VarChar
    0.31
    bet
    0.31
    Otros
    0.30
    MethodName
    0.30
    Act Density 0.029%

    No Known Activations