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

    Neuronpedia

    INDEX
    Explanations

    punctuation, numerical values, and words related to social interactions

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     akik
    -0.51
    SourceChecksum
    -0.49
     N
    -0.48
    GenerationType
    -0.48
    FunctionFlags
    -0.46
     Science
    -0.45
     للاسماء
    -0.44
    OGND
    -0.44
     sta
    -0.43
     ciencia
    -0.43
    POSITIVE LOGITS
     Wiktionnaire
    0.90
     فريبيس
    0.87
     esternos
    0.79
     Monfieur
    0.73
     raiſ
    0.69
     purpoſe
    0.69
    ſelf
    0.68
     myſelf
    0.67
     Majefty
    0.66
    RTGC
    0.63
    Act Density 1.132%

    No Known Activations