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

    Neuronpedia

    INDEX
    Explanations

    academic publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ци
    -0.07
    regs
    -0.07
     Material
    -0.07
     ery
    -0.07
     nation
    -0.06
     nineteenth
    -0.06
     одним
    -0.06
     marry
    -0.06
    enta
    -0.06
     My
    -0.06
    POSITIVE LOGITS
    dech
    0.07
     fray
    0.07
    ตำบล
    0.06
     Jakarta
    0.06
    itt
    0.06
     gson
    0.06
    CAM
    0.06
     brazil
    0.06
     Trang
    0.06
     비
    0.06
    Act Density 0.078%

    No Known Activations