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

    Neuronpedia

    INDEX
    Explanations

    Circle mathematics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    万亩
    -0.07
     Lana
    -0.07
    crets
    -0.06
     encore
    -0.06
    .portal
    -0.06
    .setWindowTitle
    -0.06
     locally
    -0.06
    )));↵
    -0.06
    abic
    -0.06
     בכל
    -0.06
    POSITIVE LOGITS
     поверхност
    0.08
    壓
    0.08
    嫭
    0.07
    ugging
    0.07
    会影响
    0.07
    距离
    0.07
     Serv
    0.07
     perseverance
    0.07
     Diese
    0.07
    ত
    0.07
    Act Density 0.004%

    No Known Activations