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

    Neuronpedia

    INDEX
    Explanations

    violent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    َت
    -0.07
    commended
    -0.06
     learners
    -0.06
    itet
    -0.06
     Mozart
    -0.06
    puty
    -0.06
    氏
    -0.06
     harbour
    -0.06
     هست
    -0.06
    ิงหาคม
    -0.06
    POSITIVE LOGITS
     ^{}
    0.07
    "os
    0.06
     sesso
    0.06
    exampleModalLabel
    0.06
     एल
    0.06
    OME
    0.06
    틱
    0.06
     servo
    0.06
     financing
    0.06
    };↵↵↵
    0.06
    Act Density 0.004%

    No Known Activations