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

    Neuronpedia

    INDEX
    Explanations

    code comments and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    1.55
    ↵↵↵
    1.13
    ↵
    1.07
    /
    1.04
    </td>
    1.00
    <strong>
    0.98
    <b>
    0.95
    ,
    0.91
    ‬
    0.88
    <h2>
    0.87
    POSITIVE LOGITS
     FIXME
    1.63
     கிஷோர்
    1.51
     TODO
    1.44
    TODO
    1.38
     eslint
    1.36
     Mỗi
    1.36
     여기에
    1.31
     clickView
    1.30
    ्टी
    1.30
    這一
    1.24
    Act Density 0.179%

    No Known Activations