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

    Neuronpedia

    INDEX
    Explanations

    entity followed by description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mannes
    0.44
    kii
    0.43
    щему
    0.42
    kien
    0.41
     Abram
    0.40
    ◜
    0.40
     Яро
    0.40
     VII
    0.39
     AISI
    0.39
    郅
    0.38
    POSITIVE LOGITS
     inquired
    0.37
     regained
    0.35
     accountable
    0.35
     latt
    0.35
     répond
    0.35
    ND
    0.34
    号
    0.34
     able
    0.34
     النوم
    0.34
     original
    0.33
    Act Density 0.002%

    No Known Activations