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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions

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

    Mathematical or code-related expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical subscripts and notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    -0.42
    –
    -0.42
    —
    -0.41
    ―
    -0.41
     Hut
    -0.40
    ·
    -0.40
    ru
    -0.38
    ​
    -0.38
    mgren
    -0.38
    рын
    -0.37
    POSITIVE LOGITS
     <=",
    1.04
    AndEndTag
    0.95
     متعلقه
    0.92
     مشين
    0.91
     мәкал
    0.88
    <sub>
    0.87
    AutoScale
    0.87
     subscript
    0.85
    styleType
    0.82
    _{
    0.82
    Act Density 1.296%

    No Known Activations