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

    Neuronpedia

    INDEX
    Explanations

    total

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _inp
    -0.06
    plication
    -0.06
     listItem
    -0.06
    '])[
    -0.06
     besar
    -0.06
    _flow
    -0.06
    ')}}↵
    -0.06
     restraint
    -0.06
     McCabe
    -0.06
     beforeEach
    -0.06
    POSITIVE LOGITS
    rott
    0.06
     قب
    0.06
     dams
    0.06
    αν
    0.06
    (btn
    0.06
     남
    0.06
     signup
    0.06
     alternate
    0.06
     Lug
    0.06
     commuting
    0.06
    Act Density 0.001%

    No Known Activations