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

    Neuronpedia

    INDEX
    Explanations

    comparative statements highlighting differences

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

    explaining a difference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XmlSchema
    -0.44
    apatalk
    -0.42
     Turquía
    -0.42
    Scorecard
    -0.42
    بوابة
    -0.41
     Suara
    -0.41
    stanza
    -0.40
    gonic
    -0.39
    abinieri
    -0.39
    最快更新
    -0.38
    POSITIVE LOGITS
     <>",
    0.54
     difference
    0.48
    SharedCtor
    0.46
    Unlike
    0.45
     DIFFERENCE
    0.44
    zeera
    0.43
    providedIn
    0.42
     Flexib
    0.42
    unlike
    0.42
     unlike
    0.42
    Act Density 0.044%

    No Known Activations