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

    Neuronpedia

    INDEX
    Explanations

    have gained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PageIndex
    0.56
    eração
    0.55
     लॉन्
    0.47
    g
    0.46
    orel
    0.45
     लिहिले
    0.45
    ESIS
    0.45
    Further
    0.44
    inture
    0.44
    RAF
    0.44
    POSITIVE LOGITS
     typedef
    0.51
    혔
    0.48
    投
    0.47
    宽
    0.46
     sillas
    0.46
     calificaciones
    0.46
     nutrientes
    0.45
    必
    0.45
    1
    0.45
    播
    0.45
    Act Density 0.000%

    No Known Activations