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

    Neuronpedia

    INDEX
    Explanations

    Scholarships and fellowships

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Take
    -0.07
     vul
    -0.07
    吐
    -0.06
     Nel
    -0.06
     قیمت
    -0.06
     Quite
    -0.06
     hot
    -0.06
    加载
    -0.06
     canal
    -0.06
    Used
    -0.06
    POSITIVE LOGITS
     дис
    0.07
    _alarm
    0.06
     prosecution
    0.06
    estureRecognizer
    0.06
     norsk
    0.06
     tua
    0.06
    descending
    0.06
    getRequest
    0.06
    _ANDROID
    0.06
     XYZ
    0.06
    Act Density 0.022%

    No Known Activations