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

    Neuronpedia

    INDEX
    Explanations

    parts of words in location names

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.47
    much
    -0.45
     much
    -0.44
    abs
    -0.43
    Se
    -0.43
    Bit
    -0.41
    Much
    -0.41
    roslav
    -0.40
     Much
    -0.40
    Bits
    -0.39
    POSITIVE LOGITS
     HttpNotFound
    0.83
    ^(@)
    0.81
     defaultstate
    0.75
    findpost
    0.74
    MENAFN
    0.71
    saraba
    0.71
    wiſe
    0.71
     Roskov
    0.70
    出版年
    0.70
     sumpay
    0.68
    Act Density 0.810%

    No Known Activations