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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exhibitions
    -0.07
    ける
    -0.07
     националь
    -0.06
    ีโ
    -0.06
    ِم
    -0.06
    “
    -0.06
    (menu
    -0.06
    (media
    -0.06
    "s
    -0.06
     Flatten
    -0.06
    POSITIVE LOGITS
     Calc
    0.07
     claw
    0.06
     sacrific
    0.06
     beste
    0.06
     Nhà
    0.06
    sess
    0.06
     delaying
    0.06
    钱
    0.06
     кал
    0.06
     Beacon
    0.06
    Act Density 0.004%

    No Known Activations