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

    Neuronpedia

    INDEX
    Explanations

    no pressure to initiate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ווי
    0.49
     einfacher
    0.46
    communic
    0.46
     أعلام
    0.45
     فس
    0.44
    Communic
    0.43
    ឪ
    0.43
     sclerosis
    0.43
    vect
    0.42
    nep
    0.41
    POSITIVE LOGITS
     FIXME
    0.49
    礫
    0.43
    しかし
    0.42
    嶼
    0.42
     Fakat
    0.41
     Making
    0.41
    и
    0.41
     alc
    0.40
     CFM
    0.39
    through
    0.39
    Act Density 0.001%

    No Known Activations