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

    Neuronpedia

    INDEX
    Explanations

    form submission submit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    m
    1.53
    k
    1.50
    g
    1.31
    l
    1.17
    ka
    1.16
    ε
    1.15
    м
    1.15
    e
    1.13
    ча
    1.13
    та
    1.13
    POSITIVE LOGITS
     Referential
    1.47
     thereof
    1.29
    endum
    1.24
     그때
    1.23
     metamorphic
    1.19
     setToDefault
    1.17
    縝
    1.15
    了一个
    1.14
     پی
    1.14
    )+"]("+
    1.12
    Act Density 0.000%

    No Known Activations