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

    Neuronpedia

    INDEX
    Explanations

    most

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    JSONArray
    -0.08
    etiyle
    -0.07
    _Parms
    -0.07
    \Query
    -0.06
    Utility
    -0.06
     seventh
    -0.06
    counts
    -0.06
    elsen
    -0.06
     assists
    -0.06
    rances
    -0.06
    POSITIVE LOGITS
    秘
    0.08
    coords
    0.07
     __('
    0.06
     nick
    0.06
     Υ
    0.06
     flawed
    0.06
     £
    0.06
     rebellion
    0.06
    λίου
    0.06
     ():
    0.06
    Act Density 0.040%

    No Known Activations