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

    Neuronpedia

    INDEX
    Explanations

    legal and political actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    m
    1.54
    й
    1.44
    ния
    1.42
    l
    1.39
    nails
    1.33
    (-
    1.30
    го
    1.28
    n
    1.28
    ន៍
    1.27
    ്
    1.27
    POSITIVE LOGITS
     remedied
    1.88
    Kemudian
    1.82
    Điều
    1.79
    −−
    1.77
     tenían
    1.68
     fué
    1.60
    गौरतलब
    1.59
     debía
    1.58
     unfounded
    1.57
    Não
    1.57
    Act Density 0.026%

    No Known Activations