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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plastics
    -0.07
    	synchronized
    -0.06
    .parameter
    -0.06
     grandfather
    -0.06
    foundation
    -0.06
     threw
    -0.06
    _es
    -0.06
     celebrated
    -0.06
    	fun
    -0.06
    	hr
    -0.06
    POSITIVE LOGITS
    :/
    0.07
     HUGE
    0.07
     hues
    0.06
     　
    0.06
    eri
    0.06
     Α
    0.06
    _artist
    0.06
    oupper
    0.06
    ải
    0.06
     Chapman
    0.06
    Act Density 0.014%

    No Known Activations