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

    Neuronpedia

    INDEX
    Explanations

    say "Id"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    提现
    -0.07
    阉
    -0.07
     Eff
    -0.07
    _MA
    -0.07
    iciar
    -0.06
    uevo
    -0.06
     Lexus
    -0.06
    _reward
    -0.06
     şeker
    -0.06
     cabinets
    -0.06
    POSITIVE LOGITS
    let
    0.08
    descriptor
    0.07
     Dương
    0.07
    都市
    0.07
    缟
    0.07
    (stop
    0.07
    (type
    0.07
    <GameObject
    0.07
    _TOO
    0.07
    .Node
    0.06
    Act Density 0.013%

    No Known Activations