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

    Neuronpedia

    INDEX
    Explanations

    classnames

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .progress
    -0.08
    είται
    -0.07
    pos
    -0.07
     bad
    -0.06
    仔
    -0.06
    κας
    -0.06
     BAD
    -0.06
     только
    -0.06
     setPassword
    -0.06
     basketball
    -0.06
    POSITIVE LOGITS
     SCH
    0.07
    vrir
    0.06
     ww
    0.06
     Fish
    0.06
    ordon
    0.06
     favourites
    0.06
    _store
    0.06
    (class
    0.05
     Arbeits
    0.05
    ,www
    0.05
    Act Density 0.000%

    No Known Activations