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

    Neuronpedia

    INDEX
    Explanations

    swear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cục
    -0.07
    -material
    -0.07
     コ
    -0.06
     flat
    -0.06
    timezone
    -0.06
    .Designer
    -0.06
    Rom
    -0.06
     Rehabilitation
    -0.06
     che
    -0.06
     Missouri
    -0.06
    POSITIVE LOGITS
    bef
    0.06
    这样
    0.06
    APTER
    0.06
     DECLARE
    0.06
    peats
    0.06
    /private
    0.06
     густ
    0.06
    grund
    0.06
    unknown
    0.06
    sending
    0.06
    Act Density 0.031%

    No Known Activations