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

    Neuronpedia

    INDEX
    Explanations

    fashion and function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ong
    0.46
    itattu
    0.42
    óc
    0.40
    模様
    0.40
    ॢ
    0.40
    ubles
    0.40
     Ong
    0.39
    ><
    0.39
     திருக்கோ
    0.39
    inez
    0.38
    POSITIVE LOGITS
     suficientemente
    0.45
     diccionario
    0.42
     hermanos
    0.41
    thur
    0.41
    çar
    0.40
     terbesar
    0.40
     Drivers
    0.39
    ו
    0.38
     sufficiently
    0.38
     Einstein
    0.38
    Act Density 0.000%

    No Known Activations