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

    Neuronpedia

    INDEX
    Explanations

    signs and symbols used in mathematical expressions or programming syntax

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

    table structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oredCriteria
    -0.86
    IntoConstraints
    -0.80
    MigrationBuilder
    -0.77
    ArrowToggle
    -0.71
     Italijanski
    -0.69
     Roskov
    -0.68
     ब्रेकडाउन
    -0.68
    fjspx
    -0.66
    errHandler
    -0.66
    estacks
    -0.65
    POSITIVE LOGITS
    <td>
    0.36
    hline
    0.33
    Text
    0.31
    From
    0.31
     Nürnberg
    0.29
                                   
    0.29
     From
    0.28
    </td>
    0.28
    ナン
    0.28
    ↵
    0.27
    Act Density 0.004%

    No Known Activations