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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _BRANCH
    -0.07
    �
    -0.07
    という
    -0.06
    irect
    -0.06
     โดย
    -0.06
     drawers
    -0.06
    ための
    -0.06
    �
    -0.06
     tong
    -0.06
    滅
    -0.06
    POSITIVE LOGITS
    iska
    0.06
     différentes
    0.06
     prat
    0.06
     성공
    0.06
    qua
    0.06
    sehen
    0.06
     shops
    0.06
    .Helper
    0.06
    rink
    0.06
     divides
    0.06
    Act Density 0.097%

    No Known Activations