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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    biology
    -0.07
     бол
    -0.06
    busters
    -0.06
    дел
    -0.06
     él
    -0.06
    edar
    -0.06
    ух
    -0.06
     summarized
    -0.06
     achievable
    -0.05
     اهمیت
    -0.05
    POSITIVE LOGITS
    ACY
    0.07
     UAE
    0.07
     đến
    0.07
    26
    0.07
    	false
    0.07
    #__
    0.06
     `{
    0.06
    _AM
    0.06
    álního
    0.06
     आव
    0.06
    Act Density 0.012%

    No Known Activations