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

    Neuronpedia

    INDEX
    Explanations

    clarification and modification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     planters
    0.43
     Economy
    0.42
     (
    0.41
     [
    0.41
     economy
    0.41
     -,
    0.40
    噜
    0.40
     理解
    0.39
     आत्म
    0.38
     pö
    0.38
    POSITIVE LOGITS
     limpeza
    0.52
    hock
    0.49
    omé
    0.49
    ただし
    0.48
     caveat
    0.47
    註
    0.46
     limpi
    0.45
    removing
    0.45
    UTION
    0.45
    加えて
    0.45
    Act Density 0.000%

    No Known Activations