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

    Neuronpedia

    INDEX
    Explanations

    job positions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    軍
    -0.07
     polite
    -0.06
     Assessment
    -0.06
     Ambassador
    -0.06
    "G
    -0.06
    Bush
    -0.06
     accommodations
    -0.06
    assador
    -0.06
     Tik
    -0.06
    Changing
    -0.06
    POSITIVE LOGITS
    .EventType
    0.07
     kills
    0.07
    سیون
    0.07
    죽
    0.07
    Hi
    0.06
     tyr
    0.06
     neck
    0.06
    toggleClass
    0.06
     karakter
    0.06
     Hi
    0.06
    Act Density 0.017%

    No Known Activations