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
    Jur
    -0.07
    ียงใหม
    -0.07
     reh
    -0.06
     są
    -0.06
    ummings
    -0.06
     공고
    -0.06
    露
    -0.06
    랜
    -0.06
     повинен
    -0.06
    FAQ
    -0.06
    POSITIVE LOGITS
    _ORD
    0.06
     conditional
    0.06
    (metadata
    0.06
    wide
    0.06
    Deque
    0.06
    .deg
    0.06
     Luca
    0.06
     ads
    0.06
    (sa
    0.06
    /custom
    0.06
    Act Density 0.040%

    No Known Activations