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

    Neuronpedia

    INDEX
    Explanations

    chaotic, difficult, eventful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     expandable
    0.66
     caché
    0.64
    ితి
    0.63
     умолчанию
    0.63
     macroscopic
    0.61
     stør
    0.60
     creato
    0.60
     vorhand
    0.59
     trustworthiness
    0.59
     Availability
    0.59
    POSITIVE LOGITS
     eventful
    2.33
     tumultuous
    2.25
     turbulent
    2.11
     chaotic
    1.96
     hectic
    1.92
     bumpy
    1.80
     stressful
    1.75
     grueling
    1.74
     harrowing
    1.69
     tense
    1.68
    Act Density 0.182%

    No Known Activations