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

    Neuronpedia

    INDEX
    Explanations

    MUST-HAVE Features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zoomSeekBar
    0.57
     récord
    0.54
    踰
    0.52
    ныгы
    0.52
    деся
    0.52
    netHex
    0.52
    работ
    0.52
    dır
    0.52
     Оюн
    0.52
    ногие
    0.51
    POSITIVE LOGITS
    one
    0.59
    ast
    0.56
    ente
    0.55
    HAR
    0.53
    VE
    0.51
    Adapter
    0.51
    akt
    0.50
    k
    0.50
    平
    0.50
    CM
    0.50
    Act Density 0.000%

    No Known Activations