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

    Neuronpedia

    INDEX
    Explanations

    preliminary/initial stage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vivo
    -0.07
     ==========
    -0.07
    .num
    -0.06
     Casino
    -0.06
     Dude
    -0.06
     not
    -0.06
     cual
    -0.06
    ogi
    -0.06
    mey
    -0.06
    (None
    -0.06
    POSITIVE LOGITS
    .vars
    0.07
     reclaim
    0.07
    inition
    0.07
    stoup
    0.07
    _apps
    0.06
    elerinde
    0.06
    alous
    0.06
    กำ
    0.06
     н
    0.06
     開
    0.06
    Act Density 0.031%

    No Known Activations