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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.60
    <bos>
    -0.57
     nahilalakip
    -0.54
    UnknownFieldSet
    -0.51
     Mald
    -0.50
    ⓧ
    -0.48
     calendriers
    -0.48
    SharedDtor
    -0.45
     geleverd
    -0.45
    unggah
    -0.44
    POSITIVE LOGITS
    httphttps
    0.65
    shoes
    0.61
    onViewCreated
    0.60
    coats
    0.59
     BoxFit
    0.58
     positifs
    0.57
     coat
    0.57
    coat
    0.56
    ftagPool
    0.55
     coats
    0.54
    Act Density 0.032%

    No Known Activations