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

    Neuronpedia

    INDEX
    Explanations

    instances of the opening parenthesis symbol

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

    programming constructs and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſche
    -0.41
    ]^{-
    -0.40
    .
    -0.37
     eloquence
    -0.37
    es
    -0.36
    </u>
    -0.35
     nghiệm
    -0.35
    </table>
    -0.35
    ES
    -0.35
     approaches
    -0.35
    POSITIVE LOGITS
     ((
    0.84
     (((
    0.79
    (((
    0.77
    =(
    0.76
    ((
    0.75
    +(
    0.71
     =(
    0.71
    =((
    0.70
    [(
    0.69
    ]=(
    0.69
    Act Density 0.042%

    No Known Activations