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

    Neuronpedia

    INDEX
    Explanations

    Rh

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ='
    -0.06
     carefully
    -0.06
    ANY
    -0.06
    DER
    -0.06
    innerText
    -0.06
    X
    -0.06
    AGER
    -0.05
     texture
    -0.05
    celain
    -0.05
    (k
    -0.05
    POSITIVE LOGITS
    ými
    0.07
     작품
    0.07
     Scala
    0.07
    Dt
    0.07
    етич
    0.06
     Dan
    0.06
     vowed
    0.06
    SocketAddress
    0.06
    Handler
    0.06
    (shared
    0.06
    Act Density 0.001%

    No Known Activations