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

    Neuronpedia

    INDEX
    Explanations

    numbers, units, or codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chunk
    0.55
     tres
    0.51
     evolving
    0.49
     high
    0.49
     particularly
    0.48
     exc
    0.48
     fer
    0.47
     higher
    0.47
     direct
    0.47
     evidenced
    0.46
    POSITIVE LOGITS
    0
    1.00
    ème
    0.81
    ۰۰
    0.77
    ⃣
    0.76
    5
    0.74
    ️⃣
    0.73
    ٠
    0.71
    8
    0.71
    th
    0.71
    yrs
    0.70
    Act Density 0.528%

    No Known Activations