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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (await
    -0.07
     Sprite
    -0.07
     مدیریت
    -0.07
     shape
    -0.06
    557
    -0.06
     ancestor
    -0.06
    ripe
    -0.06
     relay
    -0.06
    .startsWith
    -0.06
     feminist
    -0.06
    POSITIVE LOGITS
    ерим
    0.07
    ös
    0.07
     OH
    0.07
    ];↵↵↵
    0.06
    ktion
    0.06
    Mappings
    0.06
    rol
    0.06
    cion
    0.06
    ological
    0.06
     '%$
    0.06
    Act Density 0.001%

    No Known Activations