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

    Neuronpedia

    INDEX
    Explanations

    Disk space and memory

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     worrying
    -0.07
     ＼
    -0.07
    Machine
    -0.07
    严
    -0.07
     burgl
    -0.06
    类
    -0.06
     yp
    -0.06
     teenage
    -0.06
    ้นท
    -0.06
    бит
    -0.06
    POSITIVE LOGITS
    asurement
    0.07
     ATI
    0.07
     قل
    0.06
     Hos
    0.06
    _reaction
    0.06
    ccc
    0.06
    佐
    0.06
    -am
    0.06
    udiant
    0.06
    illum
    0.06
    Act Density 0.006%

    No Known Activations