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

    Neuronpedia

    INDEX
    Explanations

    in/into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    люд
    -0.07
    neğin
    -0.06
    .trigger
    -0.06
    .subtitle
    -0.06
    cer
    -0.06
     ambitious
    -0.06
    ')))
    -0.06
     наблюд
    -0.06
    generator
    -0.06
    ugins
    -0.06
    POSITIVE LOGITS
    687
    0.08
     aynı
    0.08
    Error
    0.06
     언제
    0.06
    0.06
    Ret
    0.06
    _now
    0.06
    atile
    0.06
    izzy
    0.06
     sixty
    0.06
    Act Density 0.008%

    No Known Activations