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

    Neuronpedia

    INDEX
    Explanations

    cost

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     servo
    -0.06
     admiration
    -0.06
     BW
    -0.06
     invert
    -0.06
     Saudis
    -0.06
     Madden
    -0.06
    berg
    -0.06
    pid
    -0.06
    •
    -0.06
     strings
    -0.06
    POSITIVE LOGITS
     colorWith
    0.08
    /Core
    0.06
    .getElementsByClassName
    0.06
    верж
    0.06
     Doğu
    0.06
    시험
    0.06
    _attached
    0.06
    Ability
    0.06
    ltre
    0.06
    ัญ
    0.06
    Act Density 0.002%

    No Known Activations