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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plug
    -0.08
     sedan
    -0.07
    	q
    -0.06
     lies
    -0.06
    _PHONE
    -0.06
    وجب
    -0.06
    ♓
    -0.06
    𝘵
    -0.06
     valuation
    -0.06
     configuring
    -0.06
    POSITIVE LOGITS
     mamm
    0.07
    附近
    0.07
    傣
    0.06
    同伴
    0.06
     הכר
    0.06
    percent
    0.06
    .UInt
    0.06
    真实性
    0.06
    人脸识别
    0.06
     Edgar
    0.06
    Act Density 0.080%

    No Known Activations