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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and operations

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

    Percentage calculations

    np_acts-logits-general · gemini-2.0-flash

    math and code expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.75
    __':
    -0.63
    BuildContext
    -0.60
    __':
    -0.58
    MemoryWarning
    -0.58
    MigrationBuilder
    -0.52
    EndContext
    -0.52
    providedIn
    -0.51
     itſelf
    -0.51
     himſelf
    -0.50
    POSITIVE LOGITS
    ᕗ
    0.39
     Obrador
    0.37
    bmw
    0.34
    Distribuzione
    0.34
     شب
    0.34
     Abhi
    0.33
     unless
    0.32
    penup
    0.32
     sin
    0.32
     Tä
    0.32
    Act Density 0.909%

    No Known Activations