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

    Neuronpedia

    INDEX
    Explanations

    breakdown of how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    溶液
    0.49
     greenish
    0.48
     vertebra
    0.41
    netHex
    0.41
     স্থলে
    0.41
     whitish
    0.40
    Translatef
    0.40
     údaj
    0.40
     مذکور
    0.40
     halibut
    0.40
    POSITIVE LOGITS
    Categories
    0.49
    <h4>
    0.49
     основные
    0.48
    Think
    0.47
    <h3>
    0.47
    Factors
    0.46
    Best
    0.45
    What
    0.44
    ̧
    0.44
    Understand
    0.44
    Act Density 0.234%

    No Known Activations