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

    Neuronpedia

    INDEX
    Explanations

    names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.90
    ,
    0.86
    .
    0.76
     the
    0.74
     {
    0.74
     a
    0.73
    ;
    0.70
     especially
    0.68
     information
    0.68
     edge
    0.67
    POSITIVE LOGITS
     základě
    0.82
    ฯ
    0.82
    lyPlugin
    0.81
    hetiti
    0.79
    getBlueTeam
    0.79
    getImageFolder
    0.78
     exposureButton
    0.78
    ogramDetails
    0.78
     magní
    0.78
    ંપની
    0.77
    Act Density 0.158%

    No Known Activations