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

    Neuronpedia

    INDEX
    Explanations

    mean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    成功
    -0.06
    िड
    -0.06
    晶
    -0.06
     фах
    -0.06
     Surveillance
    -0.06
     mainBundle
    -0.06
    废
    -0.06
    comed
    -0.06
    okia
    -0.06
    _FACTORY
    -0.06
    POSITIVE LOGITS
     nasty
    0.08
     paced
    0.07
     mean
    0.07
    _seek
    0.07
    nels
    0.07
    strt
    0.07
    AUSE
    0.07
     manip
    0.06
    ина
    0.06
    ordination
    0.06
    Act Density 0.012%

    No Known Activations