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

    Neuronpedia

    INDEX
    Explanations

    foundation phase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     founded
    0.71
     founder
    0.65
     found
    0.58
    founder
    0.57
     fondateur
    0.56
     Founder
    0.55
     fundada
    0.54
     founders
    0.53
     fondée
    0.51
     Founded
    0.51
    POSITIVE LOGITS
    laying
    0.78
    laid
    0.68
     laying
    0.68
     laid
    0.64
     stones
    0.63
    stone
    0.62
    stones
    0.62
    भूत
    0.59
     piedras
    0.58
    layer
    0.57
    Act Density 0.026%

    No Known Activations