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

    Neuronpedia

    INDEX
    Explanations

    Numerical measurements and doses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sns
    -0.07
     Kur
    -0.07
    除夕
    -0.07
    一同
    -0.06
     heaters
    -0.06
    学前
    -0.06
    积极性
    -0.06
     worksheets
    -0.06
     Buenos
    -0.06
     대통
    -0.06
    POSITIVE LOGITS
    ↩
    0.08
    stack
    0.07
     bypass
    0.07
    <Edge
    0.07
    /bind
    0.07
    溢
    0.06
    缴
    0.06
    signals
    0.06
     paździ
    0.06
    ogn
    0.06
    Act Density 0.359%

    No Known Activations