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

    Neuronpedia

    INDEX
    Explanations

    expressions related to methods or approaches

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

    way that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.40
    Élet
    -0.36
     hänen
    -0.35
     ausge
    -0.34
    ناك
    -0.33
     fermé
    -0.31
     gez
    -0.31
    ']));
    -0.31
     vacances
    -0.30
    Phân
    -0.30
    POSITIVE LOGITS
    MLLoader
    0.67
    SharedDtor
    0.64
     pinulongan
    0.58
     defaultstate
    0.57
     مشين
    0.55
    pity
    0.55
     somehow
    0.55
    ymce
    0.52
     Capability
    0.52
    stdbool
    0.51
    Act Density 0.009%

    No Known Activations