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

    Neuronpedia

    INDEX
    Explanations

    memory deletion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	e
    -0.07
    従
    -0.07
     RF
    -0.07
     burada
    -0.07
     semiconductor
    -0.06
     PACKET
    -0.06
     makin
    -0.06
     diagnoses
    -0.06
     Buffered
    -0.06
     наз
    -0.06
    POSITIVE LOGITS
    _sun
    0.06
     mercury
    0.06
     infring
    0.06
    anges
    0.06
    shots
    0.06
    .getLength
    0.06
     lar
    0.06
    ochond
    0.06
    entr
    0.06
    enha
    0.05
    Act Density 0.003%

    No Known Activations