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

    Neuronpedia

    INDEX
    Explanations

    types of information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.92
     [
    0.83
     **
    0.75
     -
    0.75
    .
    0.70
     /
    0.68
     which
    0.68
     .
    0.66
     (
    0.66
     initially
    0.65
    POSITIVE LOGITS
    ujących
    1.55
    AutoStabilise
    1.49
    autorBinding
    1.47
    𒐾
    1.47
     burnArea
    1.45
    ECaut
    1.45
    <unused2608>
    1.45
    <unused2311>
    1.45
     ஜீயஸின்
    1.45
    FBSDKMacros
    1.45
    Act Density 0.324%

    No Known Activations