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

    Neuronpedia

    INDEX
    Explanations

    fat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Printf
    -0.07
    \Service
    -0.07
     Mug
    -0.07
     Thursday
    -0.07
     Friday
    -0.07
     McKin
    -0.06
     Conditioning
    -0.06
    (do
    -0.06
    Ars
    -0.06
    Concern
    -0.06
    POSITIVE LOGITS
    fact
    0.06
    asive
    0.06
    SUPER
    0.06
     addButton
    0.06
     jpg
    0.05
    Inspect
    0.05
     aircraft
    0.05
     punitive
    0.05
     aşam
    0.05
     cw
    0.05
    Act Density 0.006%

    No Known Activations