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

    Neuronpedia

    INDEX
    Explanations

    Interruptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     automation
    -0.07
    .userAgent
    -0.07
     documentos
    -0.06
    _as
    -0.06
    	filter
    -0.06
     GETGLOBAL
    -0.06
     RestClient
    -0.06
    .vehicle
    -0.06
    FD
    -0.06
     Private
    -0.06
    POSITIVE LOGITS
     kız
    0.07
    査
    0.06
    Abb
    0.06
     đ
    0.06
     reopened
    0.06
    rott
    0.06
     Jug
    0.06
     eyeb
    0.06
     RL
    0.06
    婚
    0.06
    Act Density 0.001%

    No Known Activations