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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zeit
    -0.07
    偶尔
    -0.07
    大会上
    -0.07
    *"
    -0.07
     Opcode
    -0.07
    ivid
    -0.07
    pecting
    -0.07
    到底是
    -0.07
    煌
    -0.07
     Fourier
    -0.07
    POSITIVE LOGITS
    𫟅
    0.07
     cholesterol
    0.06
     numérique
    0.06
    क
    0.06
    _SOCKET
    0.06
    usband
    0.06
    Fee
    0.06
    undra
    0.06
    services
    0.06
    ADDING
    0.06
    Act Density 0.001%

    No Known Activations