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

    Neuronpedia

    INDEX
    Explanations

    milliseconds for time units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ación
    1.00
    atenate
    0.89
    at
    0.85
    ations
    0.82
     Ο
    0.82
    uls
    0.81
    ’
    0.81
    acją
    0.78
    osite
    0.77
    aban
    0.77
    POSITIVE LOGITS
    N
    1.61
    T
    1.52
    W
    1.39
    E
    1.28
    L
    1.25
    S
    1.23
    V
    1.22
    M
    1.21
    R
    1.19
    H
    1.18
    Act Density 0.010%

    No Known Activations