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

    Neuronpedia

    INDEX
    Explanations

    product specifications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     describe
    -0.07
    全景
    -0.07
    歌手
    -0.07
    omes
    -0.07
     Ned
    -0.07
    (fields
    -0.07
     CONS
    -0.06
    搐
    -0.06
     בגל
    -0.06
     governed
    -0.06
    POSITIVE LOGITS
    ��
    0.07
     Ayrıca
    0.07
    是因为
    0.07
    STRING
    0.07
    mysqli
    0.07
     Romeo
    0.07
    Erro
    0.07
    ierce
    0.07
    ु
    0.06
    节能减排
    0.06
    Act Density 0.006%

    No Known Activations