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

    Neuronpedia

    INDEX
    Explanations

    being

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     состав
    -0.07
     industry
    -0.07
    /Game
    -0.07
     worship
    -0.07
    ano
    -0.07
     fet
    -0.07
    lem
    -0.06
     circulation
    -0.06
     ice
    -0.06
    sumer
    -0.06
    POSITIVE LOGITS
    _while
    0.06
     abdominal
    0.06
    _exist
    0.06
    ?↵↵
    0.06
     fazer
    0.06
     Pipes
    0.06
    (KERN
    0.06
     personals
    0.06
    販売
    0.06
    .cloud
    0.06
    Act Density 0.017%

    No Known Activations