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

    Neuronpedia

    INDEX
    Explanations

    appropriate treatment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     않습니다
    0.45
    ("[
    0.43
     XVIII
    0.43
     retval
    0.41
     applications
    0.40
    XI
    0.40
     reduction
    0.40
     pure
    0.39
     graphite
    0.38
     mantra
    0.38
    POSITIVE LOGITS
    you
    0.47
    luft
    0.45
    kadang
    0.45
    अभिने
    0.44
    ओ
    0.44
    مکمل
    0.44
    ยาก
    0.43
     inicios
    0.43
    𝒔
    0.43
    म्पियन
    0.43
    Act Density 0.005%

    No Known Activations