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

    Neuronpedia

    INDEX
    Explanations

    questions and problem-solving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    illin
    -0.07
    .pem
    -0.06
    งช
    -0.06
    .Linear
    -0.06
     coll
    -0.06
    퓨
    -0.06
    ravel
    -0.06
     Bit
    -0.06
    pcs
    -0.06
    .Draw
    -0.06
    POSITIVE LOGITS
    _od
    0.07
    ۷
    0.07
    敏
    0.07
     COST
    0.06
     IG
    0.06
     شد
    0.06
     catast
    0.06
    ぶ
    0.06
     feel
    0.06
    ën
    0.06
    Act Density 0.001%

    No Known Activations