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

    Neuronpedia

    INDEX
    Explanations

    list items or options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ।
    1.52
     στό
    1.45
    馴染
    1.43
     Organization
    1.41
    kušen
    1.40
     મૂળ
    1.38
     ».
    1.37
     Bản
    1.37
     。
    1.37
     nominally
    1.35
    POSITIVE LOGITS
    ”、“
    1.18
    ised
    1.11
    CD
    1.09
    hyperref
    1.09
    ”“
    1.08
    akwa
    1.06
    s
    1.05
    зе
    1.04
    isselle
    1.03
    isPlaying
    1.03
    Act Density 0.000%

    No Known Activations