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

    Neuronpedia

    INDEX
    Explanations

    expressions related to emotional experiences and subjective reflections

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

    preceding common stop words

    np_acts-logits-general · gemini-2.0-flash

    progress principle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.67
    HasForeignKey
    -0.65
    tagHelperRunner
    -0.64
    verifyException
    -0.64
    ArgsConstructor
    -0.63
    principalTable
    -0.60
    TacToe
    -0.56
    addGap
    -0.56
    uxxxx
    -0.55
     nahilalakip
    -0.54
    POSITIVE LOGITS
     the
    0.76
    netbeans
    0.59
     whatever
    0.55
     entière
    0.54
     sự
    0.50
     anything
    0.50
    qxd
    0.50
     those
    0.49
    elemField
    0.48
    achau
    0.48
    Act Density 0.452%

    No Known Activations