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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Polish
    -0.29
    _drag
    -0.27
     aux
    -0.26
    æݨåĬ¨
    -0.25
     regression
    -0.25
    ander
    -0.25
     eccentric
    -0.25
    (optional
    -0.25
     Rem
    -0.25
     rem
    -0.25
    POSITIVE LOGITS
    llib
    0.32
    æĺ¯æĢİæł·
    0.27
    _BP
    0.27
    gs
    0.26
    вел
    0.25
     Bain
    0.25
     Epid
    0.24
    ideos
    0.24
    lt
    0.24
    ublic
    0.24
    Act Density 0.465%

    No Known Activations