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

    Neuronpedia

    INDEX
    Explanations

    here's a breakdown of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spool
    0.45
     fusible
    0.40
     mathemat
    0.40
     hexadecimal
    0.40
     comment
    0.39
     compute
    0.39
     पड़ता
    0.39
     Unfall
    0.39
     robustness
    0.38
    Arquivo
    0.38
    POSITIVE LOGITS
    läss
    0.47
    ücht
    0.44
     फेसबुक
    0.43
    tailed
    0.42
    懵
    0.42
    ahui
    0.41
    ígenes
    0.41
    aires
    0.41
    WhatsApp
    0.41
    اية
    0.40
    Act Density 0.018%

    No Known Activations