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

    Neuronpedia

    INDEX
    Explanations

    find and replace code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nhưng
    -0.06
    然而
    -0.06
    Nu
    -0.06
     increase
    -0.06
    _floor
    -0.06
    ]]↵↵
    -0.06
    Hor
    -0.05
    ้ท
    -0.05
    _door
    -0.05
     eyebrow
    -0.05
    POSITIVE LOGITS
     exercising
    0.07
    .dis
    0.07
     Thai
    0.07
    aleigh
    0.07
     Insight
    0.06
    _performance
    0.06
    UNE
    0.06
    -либо
    0.06
    hyper
    0.06
     Calgary
    0.06
    Act Density 0.179%

    No Known Activations