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

    Neuronpedia

    INDEX
    Explanations

    phrases related to resource limitations, scheduling, and being nearly complete.

    oai_token-act-pair · gemini-2.0-flash

    full

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adaptiveStyles
    -0.66
     surla
    -0.63
    BeginContext
    -0.59
     oprot
    -0.58
    Hochspringen
    -0.57
     onAnimation
    -0.52
    ună
    -0.52
    KeySpec
    -0.52
    migrationBuilder
    -0.52
    دانشنامهٔ
    -0.52
    POSITIVE LOGITS
     full
    1.59
     filled
    1.52
    full
    1.51
     filling
    1.46
    Full
    1.43
     Full
    1.41
     fill
    1.41
    FULL
    1.33
     FULL
    1.31
     fills
    1.31
    Act Density 1.137%

    No Known Activations