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

    Neuronpedia

    INDEX
    Explanations

    physics equations and diagrams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OfDay
    -0.07
    Showing
    -0.07
     abund
    -0.06
    opia
    -0.06
    _bind
    -0.06
     서
    -0.06
     TreeSet
    -0.06
    /gpl
    -0.06
     pravděpodob
    -0.06
    ...,
    -0.06
    POSITIVE LOGITS
    �
    0.07
    opp
    0.06
     rects
    0.06
    ď
    0.06
     broccoli
    0.06
     Copp
    0.06
    ИТ
    0.06
     compat
    0.06
     frustration
    0.06
     errno
    0.06
    Act Density 0.020%

    No Known Activations