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

    Neuronpedia

    INDEX
    Explanations

    vector

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /vue
    -0.06
     Mafia
    -0.06
     Chloe
    -0.06
    _mime
    -0.06
     Bomb
    -0.06
    	sp
    -0.06
     heroes
    -0.06
    	names
    -0.06
    icum
    -0.06
    og
    -0.06
    POSITIVE LOGITS
    _market
    0.07
     annotated
    0.06
    ある
    0.06
    _lon
    0.06
    ＼＼
    0.06
     derin
    0.06
     discount
    0.06
    ยะ
    0.06
    initely
    0.06
     الحرب
    0.06
    Act Density 0.008%

    No Known Activations