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

    Neuronpedia

    INDEX
    Explanations

    code imports and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ANES
    0.56
    τά
    0.54
     sommeil
    0.54
    erit
    0.54
    URU
    0.53
     ibid
    0.52
     postérieure
    0.51
     протягом
    0.51
     distr
    0.51
     seara
    0.50
    POSITIVE LOGITS
    на
    0.72
    aa
    0.59
    product
    0.58
     on
    0.57
    ли
    0.55
    лиза
    0.55
    clientX
    0.55
    fortune
    0.55
    يان
    0.54
    った
    0.54
    Act Density 0.032%

    No Known Activations