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

    Neuronpedia

    INDEX
    Explanations

    trying to be thorough

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সর্বাধিক
    0.33
     Juventus
    0.32
     Verfahren
    0.32
     Obtaining
    0.32
     Torrent
    0.32
     Plan
    0.32
     Plans
    0.32
     announcing
    0.31
     JAPAN
    0.30
     obtaining
    0.30
    POSITIVE LOGITS
     clarify
    0.39
    เข้าใจ
    0.38
    understand
    0.36
     clarification
    0.36
     이해
    0.35
     уточ
    0.35
    understanding
    0.35
    Maybe
    0.34
     nuanced
    0.34
     clearer
    0.33
    Act Density 0.581%

    No Known Activations