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

    Neuronpedia

    INDEX
    Explanations

    using

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thief
    -0.07
    aware
    -0.07
    _REPO
    -0.06
    arium
    -0.06
     warehouses
    -0.06
    िनक
    -0.06
    Bullet
    -0.06
    .inputs
    -0.06
     Pixels
    -0.06
    @email
    -0.06
    POSITIVE LOGITS
     ww
    0.06
     Isa
    0.06
    ovány
    0.06
    odie
    0.06
    commended
    0.06
    uyen
    0.06
    (ts
    0.06
    chluss
    0.06
     praw
    0.06
     Teil
    0.06
    Act Density 0.016%

    No Known Activations