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

    Neuronpedia

    INDEX
    Explanations

    numbers and characters within code or data formats

    oai_token-act-pair · gemini-2.0-flash

    Code and numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     supérieurs
    -0.56
     onOptions
    -0.51
    aurais
    -0.51
     ferons
    -0.50
     mourut
    -0.50
     Vikipedi
    -0.49
    5
    -0.48
    **********/
    -0.48
     Meksiku
    -0.46
    wój
    -0.46
    POSITIVE LOGITS
     Réponses
    0.72
     EClass
    0.59
    Зноскі
    0.57
    řevě
    0.54
    PhysRevD
    0.51
     jLabel
    0.50
    ingly
    0.50
    utilisons
    0.50
    AutoresizingMask
    0.48
     foco
    0.48
    Act Density 2.000%

    No Known Activations