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

    Neuronpedia

    INDEX
    Explanations

    derived from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ли
    0.71
    ды
    0.61
    <0x0D>
    0.59
    اريخ
    0.59
    어도
    0.57
    أم
    0.56
    কে
    0.55
     libres
    0.55
    اديم
    0.55
     sábado
    0.54
    POSITIVE LOGITS
    in
    0.85
    ל
    0.64
     derived
    0.60
     imports
    0.59
     imported
    0.58
    י
    0.57
    an
    0.56
    u
    0.56
    ar
    0.55
     import
    0.55
    Act Density 0.004%

    No Known Activations