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

    Neuronpedia

    INDEX
    Explanations

    around

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    puty
    -0.07
     me
    -0.07
    幫
    -0.07
    MH
    -0.07
    Explanation
    -0.07
    機會
    -0.07
    liches
    -0.07
    톧
    -0.07
    合计
    -0.07
    пл
    -0.07
    POSITIVE LOGITS
     consequently
    0.08
     consortium
    0.08
    athlete
    0.08
     knee
    0.07
    เทคโน
    0.07
    ,body
    0.07
    Autoresizing
    0.07
    FontAwesomeIcon
    0.07
    .utcnow
    0.07
     Scotch
    0.07
    Act Density 0.034%

    No Known Activations