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

    Neuronpedia

    INDEX
    Explanations

    time of day indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    1.43
    ुन
    1.04
    ल
    0.96
    t
    0.96
    под
    0.95
    ात
    0.95
    тину
    0.94
    juvant
    0.89
    el
    0.88
    ল
    0.88
    POSITIVE LOGITS
    𝗴
    1.20
     jsonObj
    1.15
    𝐫
    1.12
    fall
    1.12
    माइंडर
    1.10
     slept
    1.05
    да
    1.05
     confuse
    1.04
     incurred
    1.04
     grossesse
    1.04
    Act Density 0.093%

    No Known Activations