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

    Neuronpedia

    INDEX
    Explanations

    words and short phrases related to causality or changes.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ugo
    -0.51
    êu
    -0.48
     ViewHolder
    -0.45
    Kinds
    -0.45
    ximately
    -0.45
     manifiesto
    -0.44
     Kinds
    -0.44
    ellemző
    -0.44
    tivis
    -0.43
    RegistryLite
    -0.43
    POSITIVE LOGITS
    BASEPATH
    0.73
     تانيه
    0.70
    ScopeManager
    0.68
    AndEndTag
    0.66
    Rhestr
    0.65
     cref
    0.65
    AxisAlignment
    0.64
    alnız
    0.62
     disambiguazione
    0.62
    ArgsConstructor
    0.61
    Act Density 0.269%

    No Known Activations