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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and expressions

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

    mathematical formulas and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ｠
    -0.84
    ⁆
    -0.76
    ⤥
    -0.76
    ᯾
    -0.75
    ⭏
    -0.75
    -0.74
     esternos
    -0.74
    󰀄
    -0.73
    ſſung
    -0.73
    峫
    -0.73
    POSITIVE LOGITS
     säs
    0.38
    </i>
    0.35
     Inscrivez
    0.34
    </em>
    0.32
    </blockquote>
    0.30
    1
    0.29
     tambi
    0.29
    </code>
    0.29
    ↵
    0.29
    ientôt
    0.28
    Act Density 0.037%

    No Known Activations