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

    Neuronpedia

    INDEX
    Explanations

    Third

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bombers
    -0.07
    occus
    -0.07
    icorn
    -0.07
     Adaptive
    -0.07
     horrors
    -0.07
    .getLogin
    -0.06
    _truth
    -0.06
     •
    -0.06
    issor
    -0.06
     Bilim
    -0.06
    POSITIVE LOGITS
    /edit
    0.06
    sentence
    0.06
    (Post
    0.06
    (!$
    0.06
    _Unit
    0.06
     prov
    0.06
     doporuč
    0.06
     Plug
    0.05
     ostatní
    0.05
    .extensions
    0.05
    Act Density 0.002%

    No Known Activations