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

    Neuronpedia

    INDEX
    Explanations

    quotes followed by attribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    and
    0.46
    на
    0.46
    ag
    0.42
    ay
    0.37
    ある
    0.37
    are
    0.37
    é
    0.36
    w
    0.36
     utilisez
    0.36
     échantillons
    0.35
    POSITIVE LOGITS
    (
    0.36
    AL
    0.33
    ல்
    0.30
    ר
    0.30
    ס
    0.29
    ação
    0.29
    шого
    0.28
    )。
    0.28
    斯
    0.28
    gadas
    0.28
    Act Density 0.000%

    No Known Activations