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

    Neuronpedia

    INDEX
    Explanations

    waking up early

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lunch
    -0.88
    下午
    -0.85
     بعد
    -0.85
    Suddenly
    -0.85
    ya
    -0.83
    })$}
    -0.83
    ici
    -0.82
     مرح
    -0.82
    setTimeout
    -0.82
    Snap
    -0.82
    POSITIVE LOGITS
     early
    3.81
     Early
    2.73
     EARLY
    2.73
    early
    2.73
    Early
    2.72
    EARLY
    2.66
     рано
    2.23
    早
    2.16
     dawn
    2.09
     earliest
    2.05
    Act Density 0.028%

    No Known Activations