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

    Neuronpedia

    INDEX
    Explanations

    are been

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    save
    -0.07
     Upgrade
    -0.06
    .ticket
    -0.06
    _FLAG
    -0.06
    -0.06
     upgrade
    -0.06
     spiders
    -0.06
    -menu
    -0.06
     бути
    -0.06
    Monday
    -0.06
    POSITIVE LOGITS
    _normalize
    0.07
    ceil
    0.06
    _ssh
    0.06
    theast
    0.06
    pong
    0.06
     Fors
    0.06
     Yüz
    0.06
     commitments
    0.06
    _squared
    0.06
     müc
    0.06
    Act Density 0.054%

    No Known Activations