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

    Neuronpedia

    INDEX
    Explanations

    Scarlet Depths, Pinkal, Cherre

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noticeable
    0.47
     haze
    0.44
    к
    0.44
     عمليه
    0.43
     mechanism
    0.42
    スの
    0.42
     valuables
    0.42
     δεν
    0.42
     posit
    0.42
     of
    0.41
    POSITIVE LOGITS
    B
    0.49
     thei
    0.48
     название
    0.44
     alcalde
    0.44
    I
    0.44
    un
    0.43
    J
    0.42
    ﺩ
    0.42
    entreprise
    0.41
    juang
    0.41
    Act Density 0.144%

    No Known Activations