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

    Neuronpedia

    INDEX
    Explanations

    varying styles and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лица
    0.39
     gehen
    0.38
     posti
    0.38
     vol
    0.38
     prens
    0.38
     prosthetic
    0.37
     Đường
    0.37
     Road
    0.36
     sulla
    0.36
     ekip
    0.36
    POSITIVE LOGITS
    GAAP
    0.42
    펼
    0.41
     تاکید
    0.40
     선보
    0.40
    ക്കൂ
    0.39
    되면
    0.39
     eminently
    0.39
    OECD
    0.38
    ಳೆದ
    0.38
     enfat
    0.38
    Act Density 0.000%

    No Known Activations