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

    Neuronpedia

    INDEX
    Explanations

    formatted strings and template expressions in code

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

    code strings and templates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cromado
    -0.29
     pegatinas
    -0.27
     sintético
    -0.27
     adelante
    -0.27
     orejas
    -0.27
     desecha
    -0.26
    :
    -0.26
     koš
    -0.26
    ėms
    -0.26
    ,
    -0.26
    POSITIVE LOGITS
     transfieras
    0.85
     فريبيس
    0.81
     >=",
    0.75
    帖最后由
    0.73
    تقاوى
    0.73
     يتيمه
    0.68
     <",
    0.66
    tvguidetime
    0.65
    发表于
    0.63
     nahilalakip
    0.63
    Act Density 0.022%

    No Known Activations