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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _numero
    -0.07
    抜
    -0.06
     Welsh
    -0.06
    by
    -0.06
     vehicle
    -0.06
     aumento
    -0.06
    oksen
    -0.06
    983
    -0.06
     بیم
    -0.06
    985
    -0.06
    POSITIVE LOGITS
    (math
    0.07
     substant
    0.07
    چی
    0.07
    aoke
    0.07
     Ally
    0.06
     dedication
    0.06
     priesthood
    0.06
     advisors
    0.06
     svět
    0.06
    /auth
    0.06
    Act Density 0.057%

    No Known Activations