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

    Neuronpedia

    INDEX
    Explanations

    Excel files and publishers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Apprentice
    0.44
    Raquete
    0.43
    faulse
    0.41
    兔
    0.41
    fromDate
    0.40
    ディスク
    0.40
    usis
    0.40
    此
    0.40
    獸
    0.40
    Ⴚ
    0.40
    POSITIVE LOGITS
    Waar
    0.37
     sup
    0.35
    Har
    0.35
    Tas
    0.35
    Kep
    0.35
    Els
    0.35
     har
    0.34
    Bus
    0.34
     atro
    0.33
    Vul
    0.33
    Act Density 0.000%

    No Known Activations