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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     benchmarks
    -0.07
     ez
    -0.06
    erna
    -0.06
    форм
    -0.06
     二
    -0.06
     swap
    -0.06
    ILES
    -0.06
     descriptor
    -0.06
    щество
    -0.06
    _ctxt
    -0.06
    POSITIVE LOGITS
     елек
    0.06
     hlavy
    0.06
     Rebels
    0.06
     Genç
    0.06
     cooks
    0.06
     frustrations
    0.06
    .dataSource
    0.06
    (UnityEngine
    0.06
     Netflix
    0.06
    _qty
    0.06
    Act Density 0.064%

    No Known Activations