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

    Neuronpedia

    INDEX
    Explanations

    bash string manipulation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ticks
    -0.06
    .DataAnnotations
    -0.06
     труд
    -0.06
    Harness
    -0.06
     розмі
    -0.06
     drag
    -0.06
     installed
    -0.06
     bondage
    -0.06
     features
    -0.06
    started
    -0.06
    POSITIVE LOGITS
     điển
    0.06
     bud
    0.06
     MULT
    0.06
     memo
    0.06
    pecia
    0.06
     ๆ
    0.06
     kısa
    0.06
     Mult
    0.06
     홍
    0.06
    στη
    0.06
    Act Density 0.004%

    No Known Activations