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

    Neuronpedia

    INDEX
    Explanations

    job titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urers
    -0.07
     amateurs
    -0.07
     vulnerabilities
    -0.07
     rails
    -0.07
    Photos
    -0.07
    (Print
    -0.07
    attr
    -0.07
    ocop
    -0.06
    urances
    -0.06
    696
    -0.06
    POSITIVE LOGITS
    _bl
    0.06
     возрасте
    0.06
    株
    0.06
    lag
    0.06
    (bool
    0.06
     khi
    0.06
    EMPLATE
    0.05
     승
    0.05
    $n
    0.05
    句话
    0.05
    Act Density 0.015%

    No Known Activations