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

    Neuronpedia

    INDEX
    Explanations

    present

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jokes
    -0.09
    -oper
    -0.08
     DateTime
    -0.08
    SIDE
    -0.08
     laughter
    -0.07
    𝐲
    -0.07
    assandra
    -0.07
     rhythm
    -0.07
    ancock
    -0.07
     activating
    -0.07
    POSITIVE LOGITS
     present
    0.08
     плит
    0.07
    _table
    0.07
    .writ
    0.07
    🛵
    0.07
    We
    0.07
    玘
    0.07
     presents
    0.07
     מצוי
    0.07
     prés
    0.07
    Act Density 0.058%

    No Known Activations