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

    Neuronpedia

    INDEX
    Explanations

    numerical data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    053
    -0.08
    ainers
    -0.07
    amarin
    -0.06
    807
    -0.06
    mag
    -0.06
    หย
    -0.06
    鼓
    -0.06
     OPTIONAL
    -0.06
     fır
    -0.06
     biting
    -0.06
    POSITIVE LOGITS
    ,↵↵
    0.06
     molest
    0.06
     اطل
    0.06
    _prec
    0.06
    asmus
    0.06
     удоб
    0.06
    .FullName
    0.06
    ')↵↵
    0.06
     enthus
    0.06
    woord
    0.06
    Act Density 0.070%

    No Known Activations