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

    Neuronpedia

    INDEX
    Explanations

    behind her back

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.89
     kane
    0.62
     書い
    0.61
     carrière
    0.59
    َف
    0.59
     nemus
    0.57
     golfer
    0.57
     искать
    0.57
     wage
    0.56
    தைத்
    0.56
    POSITIVE LOGITS
     for
    0.96
     Background
    0.73
    G
    0.73
     For
    0.71
    For
    0.69
    D
    0.69
    ing
    0.66
    Background
    0.65
    M
    0.63
     Evaluation
    0.62
    Act Density 0.000%

    No Known Activations