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

    Neuronpedia

    INDEX
    Explanations

    diverse languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     समकक्ष
    0.36
    例
    0.36
     표준
    0.35
    uch
    0.35
    ahue
    0.35
     एखा
    0.34
    uo
    0.34
    enciar
    0.34
     subdirectory
    0.34
    ิจ
    0.33
    POSITIVE LOGITS
     various
    0.70
     verschillende
    0.68
     berbagai
    0.67
    様々な
    0.67
    各种
    0.66
    various
    0.65
     مختلف
    0.64
     المختلفة
    0.64
    Various
    0.64
     verschiedenen
    0.64
    Act Density 0.553%

    No Known Activations