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

    Neuronpedia

    INDEX
    Explanations

    mathematical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ong
    0.46
    ॢ
    0.46
    itattu
    0.46
    .").
    0.45
    Treasurer
    0.45
    ubles
    0.44
    模様
    0.43
     prehr
    0.43
    óc
    0.42
    ><
    0.42
    POSITIVE LOGITS
    ו
    0.50
     suficientemente
    0.49
     hermanos
    0.46
     terbesar
    0.46
     diccionario
    0.45
    thur
    0.44
    кі
    0.44
    cemos
    0.44
     ragazzi
    0.42
    ця
    0.42
    Act Density 0.002%

    No Known Activations