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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     swings
    -0.06
     brands
    -0.06
    StateManager
    -0.06
    .Abstract
    -0.06
    anguages
    -0.06
    WHO
    -0.06
    -defined
    -0.06
    提
    -0.06
    preset
    -0.06
     sensors
    -0.06
    POSITIVE LOGITS
    óst
    0.07
     bgColor
    0.06
    structors
    0.06
     stylish
    0.06
     nhé
    0.06
     město
    0.06
    neau
    0.06
    âh
    0.06
     sınır
    0.06
    praak
    0.06
    Act Density 0.013%

    No Known Activations