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

    Neuronpedia

    INDEX
    Explanations

    the main function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Arzneim
    0.46
     Sleeve
    0.45
     Hill
    0.45
     Kön
    0.44
     Lane
    0.44
    Hill
    0.44
     Boundaries
    0.44
     Rel
    0.43
     rel
    0.42
     Mec
    0.42
    POSITIVE LOGITS
    atori
    0.51
    ᅦ
    0.45
    ostante
    0.41
    дени
    0.41
    ષ્ય
    0.40
    amos
    0.39
    вого
    0.38
    taining
    0.38
     얘가
    0.38
    цо
    0.37
    Act Density 0.040%

    No Known Activations