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

    Neuronpedia

    INDEX
    Explanations

    to be verb

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izzle
    -0.09
    mailer
    -0.07
     따
    -0.07
     stalls
    -0.07
    /off
    -0.07
     الي
    -0.06
    _marks
    -0.06
     Retail
    -0.06
    луги
    -0.06
     Elem
    -0.06
    POSITIVE LOGITS
    ْع
    0.06
     praying
    0.06
    reward
    0.06
     ".↵
    0.06
    lua
    0.06
     attends
    0.06
     detected
    0.06
    _java
    0.06
    .”↵↵↵↵
    0.06
     refused
    0.06
    Act Density 0.056%

    No Known Activations