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

    Neuronpedia

    INDEX
    Explanations

    famous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gür
    -0.07
     Confidential
    -0.07
    .clientX
    -0.06
     Priest
    -0.06
     リ
    -0.06
    addock
    -0.06
     servi
    -0.06
     попыт
    -0.06
    거리
    -0.06
     totaling
    -0.06
    POSITIVE LOGITS
     famous
    0.12
     brand
    0.07
     Famous
    0.07
     Frem
    0.07
     DIRECTORY
    0.07
     tapes
    0.06
     /************************************************************************
    0.06
    -known
    0.06
    -del
    0.06
     teeth
    0.06
    Act Density 0.005%

    No Known Activations