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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Manuals
    -0.07
     copied
    -0.07
    ']]
    -0.07
    ,w
    -0.06
    URIComponent
    -0.06
    emd
    -0.06
    required
    -0.06
    requests
    -0.06
     ought
    -0.06
    ,W
    -0.06
    POSITIVE LOGITS
     Advances
    0.07
     undercover
    0.07
    期待
    0.07
     NATO
    0.07
     Viking
    0.06
     СРСР
    0.06
     #{@
    0.06
     Voyager
    0.06
    iê
    0.06
     СССР
    0.06
    Act Density 0.072%

    No Known Activations