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

    Neuronpedia

    INDEX
    Explanations

    vowels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stir
    -0.07
     tennis
    -0.07
    [])
    -0.07
    .exports
    -0.07
    .chk
    -0.06
    isches
    -0.06
    _VAL
    -0.06
    วน
    -0.06
    比赛
    -0.06
    stu
    -0.06
    POSITIVE LOGITS
     Nass
    0.06
    墨
    0.06
     Angie
    0.06
     smashed
    0.06
    .Output
    0.06
    [layer
    0.06
     الط
    0.06
     pageable
    0.06
    หน
    0.06
     Applied
    0.05
    Act Density 0.009%

    No Known Activations