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

    Neuronpedia

    INDEX
    Explanations

    et al. and so on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     circled
    0.74
     strictly
    0.64
    WAB
    0.61
    OMA
    0.61
     Opposite
    0.58
    kow
    0.58
    栖
    0.56
     conflicted
    0.56
     Strictly
    0.56
    MLS
    0.56
    POSITIVE LOGITS
     al
    2.57
     Al
    1.57
    al
    1.46
    Al
    1.44
     AL
    1.37
     અલ
    1.31
     ал
    1.30
     알
    1.28
     almak
    1.25
     аль
    1.22
    Act Density 0.057%

    No Known Activations