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

    Neuronpedia

    INDEX
    Explanations

    research proposals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _context
    -0.08
    Builder
    -0.07
    วง
    -0.07
    _widget
    -0.07
     uniform
    -0.07
    (settings
    -0.06
    edin
    -0.06
    foto
    -0.06
     صف
    -0.06
     حد
    -0.06
    POSITIVE LOGITS
    (av
    0.07
     Churchill
    0.06
    mie
    0.06
     accom
    0.06
     slap
    0.06
    _MORE
    0.06
    ROOT
    0.06
    _SO
    0.06
     Modes
    0.05
    \xf
    0.05
    Act Density 0.046%

    No Known Activations