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

    Neuronpedia

    INDEX
    Explanations

    (String

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oldown
    -0.07
     żeby
    -0.07
    雊
    -0.07
    嚷
    -0.07
    ╄
    -0.07
     linger
    -0.07
     spoken
    -0.07
     Wage
    -0.07
    .uniform
    -0.07
     '../
    -0.07
    POSITIVE LOGITS
     Cycle
    0.08
    @show
    0.08
    캥
    0.07
    cci
    0.07
    $ar
    0.07
    Ship
    0.07
    —which
    0.07
    న
    0.07
    万辆
    0.06
    ●
    0.06
    Act Density 0.002%

    No Known Activations