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

    Neuronpedia

    INDEX
    Explanations

    Scientific publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Newly
    -0.07
     verifier
    -0.07
     말했다
    -0.07
     census
    -0.06
    rored
    -0.06
    erm
    -0.06
    RATE
    -0.06
    nostic
    -0.06
    Recently
    -0.06
    رة
    -0.06
    POSITIVE LOGITS
    -cal
    0.07
     typingsJapgolly
    0.06
    	menu
    0.06
     hran
    0.06
    �
    0.06
    -root
    0.06
     �
    0.06
     société
    0.06
    -mm
    0.06
     Spears
    0.05
    Act Density 0.001%

    No Known Activations