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

    Neuronpedia

    INDEX
    Explanations

    historical and traditional contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     drawable
    0.27
    حم
    0.27
     причем
    0.27
    บบ
    0.26
     hemodynamic
    0.26
    堌
    0.26
    叓
    0.26
     azimuthal
    0.25
     toroidal
    0.25
    褪
    0.25
    POSITIVE LOGITS
     only
    0.51
    only
    0.46
     μόνο
    0.41
     فقط
    0.38
     hanya
    0.37
     только
    0.37
     sadece
    0.36
     ONLY
    0.36
     רק
    0.36
    只有
    0.35
    Act Density 0.150%

    No Known Activations