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

    Neuronpedia

    INDEX
    Explanations

    allowing users access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kal
    0.47
    springen
    0.47
    万元
    0.46
    Efter
    0.45
     Andreas
    0.44
     Kalah
    0.44
    kala
    0.44
    Walter
    0.44
    Namara
    0.43
    Huawei
    0.43
    POSITIVE LOGITS
     citas
    0.46
     scopes
    0.43
    грамм
    0.42
    ņa
    0.41
     comunicação
    0.41
     respeito
    0.41
     motions
    0.41
    ņem
    0.41
    作家
    0.40
     suporte
    0.40
    Act Density 0.000%

    No Known Activations