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

    Neuronpedia

    INDEX
    Explanations

    operation verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     メニュー
    -1.21
     poprzez
    -1.10
    下单
    -1.09
    Liefer
    -1.02
    ひた
    -1.02
    說的
    -1.01
     выбора
    -0.99
    茬
    -0.97
    al
    -0.96
    ります
    -0.95
    POSITIVE LOGITS
     and
    2.05
     processing
    1.30
    处理
    1.26
     then
    1.22
    elab
    1.13
    oció
    1.07
    эм
    1.05
     minOccurs
    1.04
     process
    1.03
    fjord
    1.03
    Act Density 0.086%

    No Known Activations