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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blueprint
    -0.07
    !↵↵↵↵
    -0.06
     grandfather
    -0.06
    MOVED
    -0.06
    排名
    -0.06
     προς
    -0.06
    ()")↵
    -0.06
    /pub
    -0.06
    *
↵
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     luxe
    0.07
     Hind
    0.06
     бюджет
    0.06
    Manual
    0.06
    ava
    0.06
    /ui
    0.06
     Ell
    0.06
    .blog
    0.06
    政
    0.06
     次
    0.06
    Act Density 0.000%

    No Known Activations