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

    Neuronpedia

    INDEX
    Explanations

    armed or med

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cow
    -0.07
    폴
    -0.07
    œur
    -0.07
     жов
    -0.07
    /book
    -0.07
    <H
    -0.07
    (ds
    -0.07
    xic
    -0.07
    -Jan
    -0.07
    .Center
    -0.07
    POSITIVE LOGITS
     armed
    0.08
     FName
    0.07
    amaha
    0.07
     Armed
    0.07
    .weapon
    0.07
    قم
    0.07
    оруж
    0.07
     bin
    0.06
    ;}↵
    0.06
    群
    0.06
    Act Density 0.005%

    No Known Activations