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

    Neuronpedia

    INDEX
    Explanations

    monkey

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ीवन
    -0.08
    ाप
    -0.07
    8
    -0.07
     çerçev
    -0.07
     Core
    -0.07
    ά
    -0.06
    6
    -0.06
    문의
    -0.06
    nama
    -0.06
     причин
    -0.06
    POSITIVE LOGITS
     parent
    0.07
     tempt
    0.06
    -scal
    0.06
    _KEYWORD
    0.06
     WARN
    0.06
     Rocket
    0.06
    [edge
    0.06
     avalanche
    0.06
     responds
    0.06
    chter
    0.06
    Act Density 0.004%

    No Known Activations