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

    Neuronpedia

    INDEX
    Explanations

    references to past actions and their impacts

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

    Tokens after common punctuation

    np_acts-logits-general · gemini-2.0-flash

    specific technical or foreign terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ✭✭
    -0.43
    schrank
    -0.42
    suri
    -0.42
    omitempty
    -0.41
     Skins
    -0.41
     second
    -0.40
     duplicate
    -0.38
    ArgsConstructor
    -0.38
    dressing
    -0.38
     stanovnika
    -0.37
    POSITIVE LOGITS
    WithIOException
    0.48
    例外
    0.45
    FieldNumber
    0.44
     PARTICULAR
    0.43
     especialmente
    0.42
     particularmente
    0.42
     particuli
    0.42
    Especially
    0.41
     excepción
    0.41
     ब्रेकडाउन
    0.41
    Act Density 0.644%

    No Known Activations