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

    Neuronpedia

    INDEX
    Explanations

    Acet, Google, Pa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     baseApiPath
    0.49
    敚
    0.41
    streetmap
    0.40
    سرائيل
    0.40
    INTa
    0.40
    ؟؟
    0.39
    ِين
    0.39
    მასრულ
    0.38
     えっと
    0.38
    ♰
    0.38
    POSITIVE LOGITS
     other
    0.50
     the
    0.45
     C
    0.44
     N
    0.43
     F
    0.43
     D
    0.40
    and
    0.39
     V
    0.39
     v
    0.38
     E
    0.38
    Act Density 0.160%

    No Known Activations