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

    Neuronpedia

    INDEX
    Explanations

    job reviews, ratings, results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surpluses
    0.42
    ंदगी
    0.37
    rarr
    0.37
    心灵
    0.36
     świet
    0.35
     trophic
    0.35
     moods
    0.34
     protég
    0.34
    humid
    0.34
     dend
    0.34
    POSITIVE LOGITS
     ·
    0.49
    ·
    0.46
    ･
    0.39
     cdot
    0.39
    ··
    0.38
    Provider
    0.37
     quá
    0.37
    itoti
    0.35
    cdot
    0.34
    NonNull
    0.34
    Act Density 0.000%

    No Known Activations