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

    Neuronpedia

    INDEX
    Explanations

    words used in Croatian relating to Facebook accounts and SMS messages

    oai_token-act-pair · gemini-2.0-flash

    Non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gmail
    -0.47
    之
    -0.46
    /
    -0.46
     giuri
    -0.43
     provecho
    -0.43
     répond
    -0.42
    or
    -0.42
    rogen
    -0.41
     taj
    -0.40
    tillo
    -0.40
    POSITIVE LOGITS
    <bos>
    2.08
    #
    0.85
    '}>
    0.81
    __':
    0.81
    __':
    0.79
    ^(@)
    0.79
    InitVars
    0.77
     itſelf
    0.76
    Życiorys
    0.75
    UnusedPrivate
    0.74
    Act Density 0.243%

    No Known Activations