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

    Neuronpedia

    INDEX
    Explanations

    fast-paced

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mara
    0.45
    hydes
    0.44
    悎
    0.42
    
    0.41
    Гра
    0.40
    RuL
    0.40
    Maharashtra
    0.39
    IZE
    0.39
    יא
    0.39
    Ak
    0.39
    POSITIVE LOGITS
    idious
    0.95
     paced
    0.90
    paced
    0.82
     fast
    0.72
     Fast
    0.64
    inating
    0.64
     moving
    0.60
    growing
    0.60
     asleep
    0.59
    lane
    0.58
    Act Density 0.024%

    No Known Activations