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

    Neuronpedia

    INDEX
    Explanations

    Bookings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .YELLOW
    -0.07
     admirable
    -0.06
    ，大
    -0.06
     yerinde
    -0.06
     Numero
    -0.06
    repeat
    -0.06
     zcela
    -0.06
    찰
    -0.06
    560
    -0.06
    vars
    -0.06
    POSITIVE LOGITS
                    
    0.07
     happening
    0.07
    พน
    0.06
     rootNode
    0.06
    _USAGE
    0.06
     enroll
    0.06
    _ack
    0.06
     düz
    0.06
    Formats
    0.06
    -mort
    0.06
    Act Density 0.003%

    No Known Activations