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

    Neuronpedia

    INDEX
    Explanations

    Strange events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Result
    -0.07
     Out
    -0.07
     Following
    -0.07
     Society
    -0.07
    ingredient
    -0.07
    ZY
    -0.06
     Week
    -0.06
     Latest
    -0.06
    /man
    -0.06
    ckpt
    -0.06
    POSITIVE LOGITS
     flair
    0.06
    resas
    0.06
    	RTCT
    0.06
    iton
    0.06
     추
    0.06
     há
    0.06
    ozí
    0.06
     longing
    0.06
    	emit
    0.06
     pH
    0.06
    Act Density 0.024%

    No Known Activations