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

    Neuronpedia

    INDEX
    Explanations

    compiled

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ria
    -0.07
     gst
    -0.07
     punished
    -0.06
     aber
    -0.06
    asuring
    -0.06
     Kills
    -0.06
    .bottom
    -0.06
    هنگ
    -0.06
     forfeiture
    -0.06
     Major
    -0.06
    POSITIVE LOGITS
    电脑
    0.07
     Attach
    0.07
    ,re
    0.06
     advisable
    0.06
     여러분
    0.06
    �
    0.06
    _totals
    0.06
    Slice
    0.06
     mediocre
    0.06
    ับความ
    0.06
    Act Density 0.012%

    No Known Activations