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

    Neuronpedia

    INDEX
    Explanations

    encoded string delimiters or quotation marks

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

    quoted values or attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plak
    -0.38
     tap
    -0.38
    Hozzáférés
    -0.37
     Sted
    -0.36
    DaoImpl
    -0.36
     deepcopy
    -0.36
     заме
    -0.35
    脚注の使い方
    -0.35
     plasti
    -0.34
     AppCompatTheme
    -0.34
    POSITIVE LOGITS
    AutoField
    0.64
    RenderAtEndOf
    0.56
    niająca
    0.48
    +#+#
    0.47
     CWE
    0.47
     punten
    0.45
    ValueGenerated
    0.45
     AssemblyTitle
    0.44
    pantalones
    0.44
    dafx
    0.44
    Act Density 0.051%

    No Known Activations