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

    Neuronpedia

    INDEX
    Explanations

    point

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     servlet
    -0.07
    892
    -0.07
    91
    -0.07
    _rating
    -0.07
     readers
    -0.07
     conformity
    -0.07
     transforming
    -0.06
     рам
    -0.06
     extrav
    -0.06
     lantern
    -0.06
    POSITIVE LOGITS
    _generated
    0.06
    eleri
    0.06
    ได
    0.06
    اعات
    0.06
    	info
    0.06
     tutti
    0.06
     PodsDummy
    0.06
    witter
    0.06
    .service
    0.06
    ycle
    0.06
    Act Density 0.000%

    No Known Activations