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

    Neuronpedia

    INDEX
    Explanations

    curly braces and their associated contents, indicating structured data or code blocks

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

    documentation parameter descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дописавши
    -0.55
     برانيه
    -0.47
     arşivlendi
    -0.46
    afficheront
    -0.44
    expandindo
    -0.43
    Parcelize
    -0.42
    DockStyle
    -0.40
    ValueGeneration
    -0.40
    SpringBootTest
    -0.39
    WithIOException
    -0.39
    POSITIVE LOGITS
    GEBURTS
    0.52
    ValueStyle
    0.46
    stance
    0.42
     hObject
    0.42
     متعلقه
    0.42
    labus
    0.42
    equalTo
    0.40
     cancelar
    0.40
     Wiktionnaire
    0.40
    bindParam
    0.40
    Act Density 0.013%

    No Known Activations