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

    Neuronpedia

    INDEX
    Explanations

    references to figures, tables, and mathematical notations within the text

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

    citations and cross-references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cœurs
    -0.31
    Consigli
    -0.31
     larmes
    -0.31
    ✭✭
    -0.30
    พาะ
    -0.29
     lèvres
    -0.29
     aprobado
    -0.28
     doigts
    -0.28
     vrais
    -0.28
    !)
    -0.28
    POSITIVE LOGITS
     للمعارف
    0.83
    DockStyle
    0.77
    CloseOperation
    0.75
    IntoConstraints
    0.74
    rungsseite
    0.69
    tagext
    0.59
    ſammen
    0.59
    itinéraire
    0.59
    RegistryLite
    0.59
    SPJ
    0.57
    Act Density 1.576%

    No Known Activations