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

    Neuronpedia

    INDEX
    Explanations

    statements about problems and possible solutions

    oai_token-act-pair · gemini-2.0-flash

    problem-solving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Towards
    -0.49
     Toward
    -0.48
     abiding
    -0.48
     Shakspeare
    -0.48
    logiques
    -0.48
     sauvages
    -0.47
    unica
    -0.46
    ']?>
    -0.46
    כו
    -0.45
    >//
    -0.45
    POSITIVE LOGITS
    MLLoader
    0.68
     cref
    0.68
     ComVisible
    0.59
     AspNetCore
    0.57
    TintMode
    0.54
    ünstig
    0.52
    agog
    0.52
    DebuggerStep
    0.51
    ثيق
    0.49
    RectangleBorder
    0.49
    Act Density 0.413%

    No Known Activations