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

    Neuronpedia

    INDEX
    Explanations

    code following a period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     VoIP
    0.61
    —
    0.58
     -
    0.57
     Candida
    0.56
     Photoshop
    0.55
     narciss
    0.55
     Autodesk
    0.55
     PowerPoint
    0.54
     Pilates
    0.54
     Pythagorean
    0.54
    POSITIVE LOGITS
    .*;
    0.86
    .{
    0.66
    .${
    0.58
    .
    0.55
    .,"
    0.54
    ._
    0.53
    .`
    0.53
    ‌.
    0.53
    .*
    0.52
    .??
    0.51
    Act Density 0.141%

    No Known Activations