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

    Neuronpedia

    INDEX
    Explanations

    breathing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hisset
    -0.07
     이동
    -0.06
     रहत
    -0.06
    ी।↵
    -0.06
     سرعت
    -0.06
    یت
    -0.06
    fallback
    -0.06
     교
    -0.06
     черв
    -0.06
    .Sprite
    -0.06
    POSITIVE LOGITS
    Award
    0.07
     pont
    0.07
    ąż
    0.07
     Ban
    0.07
    perform
    0.07
     scor
    0.07
    omor
    0.06
    \r
    0.06
    콜
    0.06
     Claims
    0.06
    Act Density 0.003%

    No Known Activations