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

    Neuronpedia

    INDEX
    Explanations

    non-breaking spaces andnbsp

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urii
    0.96
    zelfde
    0.94
    an
    0.93
    mets
    0.93
    dien
    0.92
    rets
    0.91
    l
    0.91
    tos
    0.88
    mation
    0.88
    igations
    0.88
    POSITIVE LOGITS
    ון
    1.07
    та
    0.96
    о
    0.96
    つ
    0.90
    а
    0.89
    会
    0.89
    EN
    0.86
    );}
    0.86
    日が
    0.86
    を変
    0.85
    Act Density 0.002%

    No Known Activations