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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nhiễm
    -0.07
    .opts
    -0.07
    러리
    -0.07
     فرو
    -0.07
    _READY
    -0.06
     Aware
    -0.06
    _curr
    -0.06
     Như
    -0.06
    WRAPPER
    -0.06
    受到
    -0.06
    POSITIVE LOGITS
    ？
    0.07
    homepage
    0.06
    (hist
    0.06
     gli
    0.06
    outed
    0.06
    smart
    0.06
     Γ
    0.06
     jumping
    0.06
     velit
    0.06
     POLIT
    0.06
    Act Density 0.033%

    No Known Activations