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

    Neuronpedia

    INDEX
    Explanations

    scientific studies abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AC
    -0.07
     markers
    -0.07
    hecy
    -0.07
    .AddInParameter
    -0.06
     payload
    -0.06
    -k
    -0.06
     cylinders
    -0.06
     wk
    -0.06
    urnal
    -0.06
    Analyzer
    -0.06
    POSITIVE LOGITS
    (KEY
    0.08
    .nick
    0.07
     Fritz
    0.07
    adresse
    0.06
     энерг
    0.06
     submar
    0.06
     řada
    0.06
    benhavn
    0.06
    _UTF
    0.06
     scams
    0.06
    Act Density 0.256%

    No Known Activations