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

    Neuronpedia

    INDEX
    Explanations

    as a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     që
    0.24
     sabemos
    0.23
     với
    0.22
     säger
    0.22
     është
    0.21
     која
    0.21
     mężczy
    0.21
     clockRadius
    0.21
     się
    0.20
     cuja
    0.20
    POSITIVE LOGITS
     an
    0.34
     a
    0.33
     "
    0.23
    a
    0.22
     tools
    0.21
    an
    0.20
     einer
    0.20
     evidence
    0.20
     A
    0.19
     Source
    0.19
    Act Density 0.337%

    No Known Activations