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

    Neuronpedia

    INDEX
    Explanations

    hearing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Project
    -0.07
     HTC
    -0.07
    いつも
    -0.07
     nextProps
    -0.07
     хорош
    -0.07
    仆
    -0.07
     Basket
    -0.07
     المعارضة
    -0.07
    וק
    -0.07
    vp
    -0.07
    POSITIVE LOGITS
    .fecha
    0.07
    تسليم
    0.07
    地理
    0.07
     aided
    0.06
    ﱈ
    0.06
     ceremon
    0.06
    ၼ
    0.06
     fidelity
    0.06
    ştır
    0.06
    uner
    0.06
    Act Density 0.004%

    No Known Activations