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

    Neuronpedia

    INDEX
    Explanations

    terms related to numerical methods and simulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    grids, steps, and intervals

    np_acts-logits-general · gemini-2.0-flash

    finer grid resolution and steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.80
     >=",
    -0.72
    Personendaten
    -0.56
    WireFormat
    -0.51
    insegna
    -0.50
     useAuth
    -0.49
     logits
    -0.48
     Circ
    -0.48
    CppCodeGen
    -0.48
     Réponses
    -0.47
    POSITIVE LOGITS
     discretization
    0.95
     step
    0.94
     finer
    0.90
     resolution
    0.87
     grid
    0.86
    step
    0.82
     Шаг
    0.82
     fine
    0.80
     шаг
    0.79
    grid
    0.77
    Act Density 1.670%

    No Known Activations