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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    传达
    -0.07
    陣
    -0.07
     RTWF
    -0.07
     którzy
    -0.07
    �
    -0.07
     аб
    -0.07
     addUser
    -0.07
     /.
    -0.06
    千方
    -0.06
     Harr
    -0.06
    POSITIVE LOGITS
    .window
    0.07
    VERTISEMENT
    0.07
    .rgb
    0.07
    ducible
    0.07
    riminator
    0.07
    .loop
    0.07
    了吧
    0.07
    .Destroy
    0.06
    📼
    0.06
    letion
    0.06
    Act Density 0.020%

    No Known Activations