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

    Neuronpedia

    INDEX
    Explanations

    university degrees

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    XH
    -0.07
    affle
    -0.07
    RETURN
    -0.06
    xdf
    -0.06
     daycare
    -0.06
     perse
    -0.06
    ivable
    -0.06
    midt
    -0.06
    =
    -0.06
    она
    -0.06
    POSITIVE LOGITS
    .Inter
    0.07
     scripting
    0.07
     Wood
    0.07
     Kentucky
    0.06
    ross
    0.06
    chartInstance
    0.06
    bai
    0.06
    ufacturer
    0.06
    $password
    0.06
     نتیجه
    0.06
    Act Density 0.025%

    No Known Activations