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

    Neuronpedia

    INDEX
    Explanations

    maker spaces and culture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.71
    ig
    0.58
    ت
    0.57
    g
    0.55
    라
    0.52
    一
    0.52
    치
    0.52
    H
    0.51
    ై
    0.50
    i
    0.50
    POSITIVE LOGITS
     essendo
    0.55
     adatto
    0.55
    ’
    0.53
    📍
    0.51
     nást
    0.50
     aliran
    0.50
    ’”
    0.50
    atorii
    0.49
    Translatef
    0.49
     seraient
    0.49
    Act Density 0.001%

    No Known Activations