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

    Neuronpedia

    INDEX
    Explanations

    Samples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     toxins
    -0.07
     JVM
    -0.07
     stress
    -0.07
    ported
    -0.06
    .dc
    -0.06
    。",↵
    -0.06
    .Per
    -0.06
    .H
    -0.06
    oha
    -0.06
    ้องน
    -0.06
    POSITIVE LOGITS
     Maurice
    0.07
     пласти
    0.07
     sahip
    0.06
     ثم
    0.06
    effective
    0.06
    _filled
    0.06
     trận
    0.06
    WithOptions
    0.06
     retrospective
    0.06
     Mori
    0.06
    Act Density 0.023%

    No Known Activations