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

    Neuronpedia

    INDEX
    Explanations

    engage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -operation
    -0.07
     prescription
    -0.06
     innovations
    -0.06
    	items
    -0.06
    BitFields
    -0.06
    床
    -0.06
     Funktion
    -0.06
    นด
    -0.06
     Cros
    -0.06
     handwritten
    -0.06
    POSITIVE LOGITS
    IRC
    0.07
    (segment
    0.06
    월까지
    0.06
    .Caption
    0.06
     درمان
    0.06
     Initiative
    0.06
    叫
    0.06
    Instrument
    0.06
     генера
    0.06
     Instrument
    0.06
    Act Density 0.000%

    No Known Activations