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

    Neuronpedia

    INDEX
    Explanations

    how to use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    selves
    1.73
    ঠ
    1.51
    可以说
    1.46
    水泥
    1.46
     불구하고
    1.32
    ed
    1.27
    versions
    1.27
    ü
    1.25
    resolvers
    1.23
    我
    1.23
    POSITIVE LOGITS
     compartido
    1.63
    寿命
    1.63
    ர்
    1.56
    АС
    1.48
     परेशान
    1.44
    িক
    1.42
     caution
    1.39
     circunferencia
    1.38
    рия
    1.37
    isable
    1.37
    Act Density 0.411%

    No Known Activations