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

    Neuronpedia

    INDEX
    Explanations

    alternatives or instead

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mysticism
    0.45
     confusion
    0.44
    confusion
    0.40
    OCUS
    0.40
    corruption
    0.39
     hypocrisy
    0.38
     efficace
    0.38
     corruption
    0.38
    chaos
    0.38
     अनियमित
    0.38
    POSITIVE LOGITS
    代わりに
    0.81
     вместо
    0.80
     instead
    0.80
    替代
    0.77
    代替
    0.75
     substitutions
    0.73
     замены
    0.71
     substitution
    0.70
    取代
    0.70
     Instead
    0.70
    Act Density 0.159%

    No Known Activations