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

    Neuronpedia

    INDEX
    Explanations

    English history events

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cream
    0.85
    Cream
    0.76
     Cuy
    0.76
     Chiefs
    0.75
    дын
    0.75
    Гу
    0.75
     Cromwell
    0.74
    ôn
    0.73
    Gil
    0.73
    Queens
    0.72
    POSITIVE LOGITS
     gto
    0.80
     kpc
    0.76
    rnd
    0.76
     htob
    0.74
    izontally
    0.72
     rmse
    0.71
    ﻓ
    0.71
    िसो
    0.71
    metto
    0.70
     rnb
    0.70
    Act Density 0.000%

    No Known Activations