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

    Neuronpedia

    INDEX
    Explanations

    UI Panel, Document, Off

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ·
    0.45
    RING
    0.44
    lains
    0.43
     نی
    0.42
    动物
    0.42
    笼
    0.42
    codiles
    0.41
     temptations
    0.41
    Ā
    0.41
     Afgh
    0.41
    POSITIVE LOGITS
     intersects
    0.62
     giữa
    0.54
     quedan
    0.51
     correctamente
    0.48
     increases
    0.48
     queda
    0.47
     quedando
    0.47
    संचार
    0.46
     tuyển
    0.44
     đều
    0.43
    Act Density 0.000%

    No Known Activations