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

    Neuronpedia

    INDEX
    Explanations

    Location/Time reference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     два
    -0.07
    oure
    -0.06
    线
    -0.06
    508
    -0.06
     Ev
    -0.06
     apl
    -0.06
    �始
    -0.06
    ighting
    -0.06
    article
    -0.06
     stanza
    -0.06
    POSITIVE LOGITS
     obsah
    0.07
    _cliente
    0.06
    _nome
    0.06
    .Brand
    0.06
     Sovere
    0.06
    _$_
    0.06
    :item
    0.06
     HM
    0.06
     fn
    0.06
    -function
    0.06
    Act Density 0.145%

    No Known Activations