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

    Neuronpedia

    INDEX
    Explanations

    instructions and usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     πρώτη
    0.49
     וה
    0.44
     ਅਤੇ
    0.44
     και
    0.44
    ⿵
    0.43
     OSError
    0.43
    വിലെ
    0.43
    和
    0.42
    isot
    0.40
    orkan
    0.40
    POSITIVE LOGITS
     améli
    0.45
     máscara
    0.45
    禳
    0.45
     penit
    0.44
     ralent
    0.44
    ന്യാ
    0.44
     conveniently
    0.43
     mél
    0.43
    reux
    0.42
     régl
    0.41
    Act Density 0.012%

    No Known Activations