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

    Neuronpedia

    INDEX
    Explanations

    For

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     to
    -0.07
    �
    -0.07
     イ
    -0.07
     polishing
    -0.06
     an
    -0.06
     biến
    -0.06
     their
    -0.06
    owitz
    -0.06
    投注
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     For
    0.09
    .For
    0.08
    】↵
    0.08
    (for
    0.07
    Server
    0.07
    For
    0.07
     riêng
    0.07
    \'
    0.06
     baseUrl
    0.06
    InputLabel
    0.06
    Act Density 0.062%

    No Known Activations