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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    束
    -0.07
    istogram
    -0.07
    ics
    -0.07
     absol
    -0.07
    YGON
    -0.06
     giver
    -0.06
     VARCHAR
    -0.06
    cole
    -0.06
    bcc
    -0.06
     Ded
    -0.06
    POSITIVE LOGITS
     cham
    0.06
    AVIS
    0.06
    лиз
    0.06
     besie
    0.06
     evade
    0.06
     nye
    0.05
     utilized
    0.05
     browsing
    0.05
     DJ
    0.05
    LT
    0.05
    Act Density 0.083%

    No Known Activations