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

    Neuronpedia

    INDEX
    Explanations

    Agreement/Confirmation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     자료
    -0.07
     in
    -0.06
    Pin
    -0.06
     avg
    -0.06
     shed
    -0.06
     recoil
    -0.06
     fontStyle
    -0.06
     Forbes
    -0.06
     التر
    -0.06
     superf
    -0.06
    POSITIVE LOGITS
    �
    0.07
    RSpec
    0.06
    �
    0.06
    PagerAdapter
    0.06
    ViewSet
    0.06
    $options
    0.06
    otionEvent
    0.06
     fq
    0.06
     Vak
    0.06
    HostName
    0.06
    Act Density 0.016%

    No Known Activations