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

    Neuronpedia

    INDEX
    Explanations

    = character usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.36
     〢
    0.33
     Crohn
    0.30
    —.
    0.30
     an
    0.29
    Jähr
    0.28
    élevage
    0.28
    StillWater
    0.28
     Vereinigten
    0.27
    ;&#
    0.27
    POSITIVE LOGITS
    на
    0.51
    i
    0.50
    ون
    0.48
    ста
    0.47
    માં
    0.47
    ни
    0.46
    ர்
    0.44
    ي
    0.43
    다
    0.43
    z
    0.42
    Act Density 0.167%

    No Known Activations