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

    Neuronpedia

    INDEX
    Explanations

    still a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chemins
    0.43
     pit
    0.41
     vorgesch
    0.40
     PIC
    0.39
     W
    0.38
     were
    0.38
     currents
    0.38
    arote
    0.38
     came
    0.38
     bats
    0.38
    POSITIVE LOGITS
     साइनस
    0.48
    بە
    0.46
    ମ୍
    0.45
     مصروف
    0.44
    々と
    0.43
    Однако
    0.42
     Scienze
    0.42
    ]，
    0.42
     cliquer
    0.41
    DanhMucSP
    0.41
    Act Density 0.002%

    No Known Activations