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

    Neuronpedia

    INDEX
    Explanations

    change types, start dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ق
    0.72
     журнала
    0.71
     дорого
    0.70
    Preparing
    0.69
    рование
    0.68
    ровании
    0.68
    का
    0.67
    Jimmy
    0.66
    スカート
    0.66
    Conflict
    0.66
    POSITIVE LOGITS
    nt
    0.88
    ﻱ
    0.87
     dominance
    0.86
    rk
    0.85
    lus
    0.84
    recipes
    0.81
    ati
    0.80
    descriptors
    0.80
    ra
    0.78
    ia
    0.78
    Act Density 0.005%

    No Known Activations