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

    Neuronpedia

    INDEX
    Explanations

    Months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .serv
    -0.07
     Bread
    -0.07
    responseObject
    -0.06
    yang
    -0.06
    parameters
    -0.06
    悟
    -0.06
    obus
    -0.06
     worlds
    -0.06
    forall
    -0.06
    ambda
    -0.06
    POSITIVE LOGITS
     ww
    0.07
     intox
    0.07
    VOKE
    0.07
     dumpsters
    0.07
     closets
    0.06
    _average
    0.06
     rotates
    0.06
     [/
    0.06
    挥
    0.06
     Pic
    0.06
    Act Density 0.009%

    No Known Activations