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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting symbols used in academic texts

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

    opening quote after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.81
    makeConstraints
    -0.59
     enggak
    -0.53
     виправивши
    -0.52
    colgante
    -0.51
     εύ
    -0.49
    ésult
    -0.49
    Diwedd
    -0.48
    pecabe
    -0.48
     <>",
    -0.48
    POSITIVE LOGITS
    ArgsConstructor
    0.51
    ✨:
    0.38
     ‘
    0.37
     “
    0.37
    SerializedName
    0.37
     Hilary
    0.37
    XDECREF
    0.37
     "
    0.36
     חיצוניים
    0.35
     mirage
    0.35
    Act Density 0.002%

    No Known Activations