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

    Neuronpedia

    INDEX
    Explanations

    describing difficulty or chaos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     attractiveness
    0.70
     incap
    0.68
     sẵn
    0.67
     caché
    0.66
     uporab
    0.66
     deficiency
    0.66
     trustworthiness
    0.65
     erhält
    0.63
     offended
    0.63
     responsiveness
    0.62
    POSITIVE LOGITS
     eventful
    2.09
     tumultuous
    1.88
     turbulent
    1.69
     tense
    1.67
     chaotic
    1.65
     hectic
    1.63
     fraught
    1.52
     stressful
    1.48
     bumpy
    1.44
     tumult
    1.38
    Act Density 0.386%

    No Known Activations