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

    Neuronpedia

    INDEX
    Explanations

    list and representation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     préférence
    0.54
    㖪
    0.50
     escala
    0.50
    কেন্দ্র
    0.50
    يير
    0.48
    绻
    0.48
    Todas
    0.47
     колеба
    0.47
     שלו
    0.47
     preferencia
    0.47
    POSITIVE LOGITS
    vasive
    0.45
     crashes
    0.45
     volition
    0.44
    ets
    0.43
    도
    0.43
    kin
    0.43
    стью
    0.42
     symmetrical
    0.42
    ñones
    0.41
     symmetry
    0.41
    Act Density 0.000%

    No Known Activations