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

    Neuronpedia

    INDEX
    Explanations

    code related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Thread
    -0.06
    (bounds
    -0.06
    pytest
    -0.06
     brighter
    -0.06
    .JButton
    -0.06
    /cards
    -0.06
     bitch
    -0.06
    uada
    -0.05
    .binding
    -0.05
    gear
    -0.05
    POSITIVE LOGITS
    remark
    0.07
     ves
    0.07
    รณ
    0.07
    acam
    0.07
    antics
    0.07
    і
    0.07
     midi
    0.07
    رف
    0.07
     Ves
    0.07
     ам
    0.07
    Act Density 0.001%

    No Known Activations