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

    Neuronpedia

    INDEX
    Explanations

    say "ities"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    addComponent
    -0.07
     announce
    -0.07
    -0.06
    Ghost
    -0.06
    (nil
    -0.06
    inu
    -0.06
    	stmt
    -0.06
     Quran
    -0.06
     theological
    -0.06
    .menuStrip
    -0.06
    POSITIVE LOGITS
    Likes
    0.06
    �
    0.06
     tasted
    0.06
    ΗΜ
    0.06
     cosas
    0.06
    -Class
    0.06
    Clean
    0.06
    	em
    0.06
     LTC
    0.05
    /apps
    0.05
    Act Density 0.002%

    No Known Activations