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

    Neuronpedia

    INDEX
    Explanations

    beneath the surface; cpp

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     griega
    0.82
     ingreso
    0.81
     scanf
    0.81
     evidently
    0.79
     गौरतलब
    0.75
     placés
    0.75
    jLabel
    0.75
     dubbio
    0.73
     dúvida
    0.73
     cigarettes
    0.73
    POSITIVE LOGITS
    Surface
    0.79
    sle
    0.70
    trav
    0.68
     Surface
    0.67
    Diffuse
    0.67
    surface
    0.65
    ोला
    0.64
    Professional
    0.63
    sit
    0.61
     surface
    0.61
    Act Density 0.015%

    No Known Activations