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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UFC
    -0.06
     and
    -0.06
    ThreadPool
    -0.06
     Jer
    -0.06
    육
    -0.06
     fick
    -0.06
     гр
    -0.06
    .style
    -0.05
     air
    -0.05
     UE
    -0.05
    POSITIVE LOGITS
    to
    0.07
    _tol
    0.07
    μπ
    0.07
    _ctrl
    0.07
     onay
    0.06
    (;
    0.06
    ایی
    0.06
     για
    0.06
    合格
    0.06
    _to
    0.06
    Act Density 0.048%

    No Known Activations