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

    Neuronpedia

    INDEX
    Explanations

    string interpolation and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    …)
    0.77
    ·
    0.76
    ...)
    0.74
    .),
    0.73
    }$.)
    0.73
    )...
    0.70
     fascist
    0.69
    ‘
    0.69
     also
    0.67
    }',
    0.67
    POSITIVE LOGITS
     ${
    1.77
    (${
    1.59
    /${
    1.56
    "${
    1.52
    ${
    1.51
     <%=
    1.47
     <?=
    1.45
     '${
    1.44
     $[
    1.43
    -${
    1.42
    Act Density 0.368%

    No Known Activations