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

    Neuronpedia

    INDEX
    Explanations

    markedly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Congress
    -0.08
    됩
    -0.08
     obtains
    -0.08
    ViewState
    -0.07
    InitialState
    -0.07
    ượng
    -0.07
    hands
    -0.07
    OPSIS
    -0.07
    уществ
    -0.07
    抓紧
    -0.07
    POSITIVE LOGITS
     Shower
    0.08
     ка
    0.07
     cuc
    0.07
    AC
    0.07
     Jad
    0.06
     Views
    0.06
     dum
    0.06
    .stack
    0.06
    especially
    0.06
     Newly
    0.06
    Act Density 0.013%

    No Known Activations