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

    Neuronpedia

    INDEX
    Explanations

    flu

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    m
    1.09
    larının
    0.97
    nél
    0.88
    ación
    0.86
    larından
    0.85
    ння
    0.84
    ography
    0.84
    ições
    0.84
     exuberant
    0.84
    et
    0.83
    POSITIVE LOGITS
    ו
    1.20
    W
    1.09
    O
    1.07
    BE
    0.98
    N
    0.96
    ু
    0.94
    the
    0.93
     perspect
    0.91
     flu
    0.90
    K
    0.88
    Act Density 0.002%

    No Known Activations