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

    Neuronpedia

    INDEX
    Explanations

    cls/clear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     driver
    -0.07
     men
    -0.07
     tone
    -0.07
    arker
    -0.07
    Ն
    -0.07
    stry
    -0.07
     GetString
    -0.07
    lier
    -0.07
     Husband
    -0.06
     Sink
    -0.06
    POSITIVE LOGITS
     הקוד
    0.08
    就来看看
    0.08
     =================================================================================
    0.07
    .j
    0.07
     Abram
    0.07
     yg
    0.07
    .padding
    0.07
     아마
    0.07
    際に
    0.07
    只怕
    0.07
    Act Density 0.003%

    No Known Activations