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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     прид
    -0.09
    .abspath
    -0.07
    ोह
    -0.07
    bv
    -0.06
    esta
    -0.06
    RESET
    -0.06
     trembling
    -0.06
     Corn
    -0.06
    ่นเกม
    -0.06
    slope
    -0.06
    POSITIVE LOGITS
     cinsel
    0.07
    )=
    0.07
    DEV
    0.07
     zaměst
    0.07
     mô
    0.06
    national
    0.06
     Ethnic
    0.06
    ného
    0.06
    Va
    0.06
    ρο
    0.06
    Act Density 0.147%

    No Known Activations