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

    Neuronpedia

    INDEX
    Explanations

    Math/logic puzzles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    müş
    -0.07
     comer
    -0.07
     Ellison
    -0.07
    leyin
    -0.06
     amacıyla
    -0.06
    .currentTime
    -0.06
     těch
    -0.06
     Sanders
    -0.06
    .KeyEvent
    -0.06
    чного
    -0.06
    POSITIVE LOGITS
     methodologies
    0.08
     Manila
    0.06
    须
    0.06
     apar
    0.06
    .ImageField
    0.06
     discriminate
    0.06
     billing
    0.06
    (env
    0.06
    otch
    0.05
    .visitMethod
    0.05
    Act Density 0.038%

    No Known Activations