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

    Neuronpedia

    INDEX
    Explanations

    bob

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ACLE
    -0.06
     관련
    -0.06
     deliberately
    -0.06
     초
    -0.06
    _ITER
    -0.06
     освіти
    -0.06
     Гор
    -0.06
     datasets
    -0.06
     flourishing
    -0.06
    pees
    -0.05
    POSITIVE LOGITS
    <label
    0.07
     bás
    0.07
    ousands
    0.07
    neath
    0.07
    英雄
    0.07
     Buffett
    0.06
     '-
    0.06
    zdy
    0.06
    gratis
    0.06
    opp
    0.06
    Act Density 0.023%

    No Known Activations