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

    Neuronpedia

    INDEX
    Explanations

    PUCT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    0.56
     Bremer
    0.46
    다음
    0.44
    남
    0.43
    阻
    0.43
    ిన
    0.42
    온
    0.42
    רים
    0.42
    ール
    0.41
    南
    0.41
    POSITIVE LOGITS
    emple
    0.57
    edì
    0.53
    tama
    0.53
     Frente
    0.53
    dard
    0.53
    gota
    0.52
    ed
    0.52
    də
    0.52
    kere
    0.52
    t
    0.52
    Act Density 0.000%

    No Known Activations