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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jay
    -0.07
     perception
    -0.07
     }),↵↵
    -0.07
    ClientId
    -0.06
     whim
    -0.06
     somebody
    -0.06
     Cinder
    -0.06
     Chaos
    -0.06
    殺
    -0.06
    Approved
    -0.06
    POSITIVE LOGITS
    ibilidad
    0.07
     Regel
    0.06
    _framework
    0.06
     strán
    0.06
    ampled
    0.06
     Beh
    0.06
    pper
    0.06
     Đảng
    0.06
     Cumhuriyeti
    0.06
    uger
    0.06
    Act Density 0.029%

    No Known Activations