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

    Neuronpedia

    INDEX
    Explanations

    domain names and email addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     waxes
    0.60
     worms
    0.59
     remercie
    0.57
     wiser
    0.57
     chúng
    0.57
     chemicals
    0.56
     blotting
    0.56
     tropic
    0.55
     näch
    0.55
     للب
    0.55
    POSITIVE LOGITS
    Visual
    0.50
    Daten
    0.48
     Visual
    0.47
    Dont
    0.47
    visual
    0.46
    Template
    0.46
    website
    0.45
    Traditional
    0.45
     Trail
    0.45
    HUD
    0.44
    Act Density 0.001%

    No Known Activations