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

    Neuronpedia

    INDEX
    Explanations

    CSS button styles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uously
    1.04
    ের
    1.03
     confound
    1.03
    in
    1.03
    ,\,
    1.00
    iousness
    0.99
    fstream
    0.99
     omission
    0.99
     IANS
    0.99
    heiros
    0.97
    POSITIVE LOGITS
    antaranya
    1.18
     Trotz
    0.98
    sgál
    0.89
     bawah
    0.88
     ആണ്
    0.88
     Tahun
    0.88
    ลม
    0.86
    edad
    0.85
    Greeting
    0.85
     merupakan
    0.84
    Act Density 0.001%

    No Known Activations