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

    Neuronpedia

    INDEX
    Explanations

    digit

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    演绎
    -0.07
     luego
    -0.07
    成交
    -0.07
     młodzie
    -0.06
     Lifetime
    -0.06
     spectra
    -0.06
     crystal
    -0.06
     subsidies
    -0.06
    must
    -0.06
    אחר
    -0.06
    POSITIVE LOGITS
     healer
    0.08
    七十
    0.08
    一个小时
    0.07
    >}↵
    0.07
    OKEN
    0.07
    פרד
    0.07
    <Transform
    0.07
    ']}↵
    0.06
    /debug
    0.06
     Outer
    0.06
    Act Density 0.000%

    No Known Activations