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

    Neuronpedia

    INDEX
    Explanations

    Work environment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adle
    -0.07
    equal
    -0.07
    =_('
    -0.07
    ADR
    -0.07
    apur
    -0.07
    aks
    -0.06
    اوي
    -0.06
    	cv
    -0.06
    =pd
    -0.06
    Pel
    -0.06
    POSITIVE LOGITS
     Mushroom
    0.07
     explosives
    0.06
     verbally
    0.06
    SERVER
    0.06
     freeze
    0.06
     доп
    0.06
     cc
    0.06
    必
    0.06
    鮮
    0.06
     своими
    0.06
    Act Density 0.015%

    No Known Activations