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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    infos
    -0.07
     Newsp
    -0.07
    nob
    -0.06
    bitrary
    -0.06
    ypy
    -0.06
    保護
    -0.06
    =os
    -0.06
    /pol
    -0.06
     양
    -0.06
     Outreach
    -0.06
    POSITIVE LOGITS
    PathComponent
    0.07
    GreaterThan
    0.06
    Pages
    0.06
     adulthood
    0.06
     southern
    0.06
    323
    0.06
     enlightenment
    0.06
     tropical
    0.06
     ParseException
    0.06
     predict
    0.06
    Act Density 0.000%

    No Known Activations