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

    Neuronpedia

    INDEX
    Explanations

    few vignettes or scenes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ighters
    0.43
     compilers
    0.40
     places
    0.38
     IPs
    0.38
    atta
    0.38
     marinas
    0.37
     adjectives
    0.36
     websites
    0.36
     Websites
    0.36
     معروف
    0.35
    POSITIVE LOGITS
     vignettes
    0.62
     tableaux
    0.59
     vignette
    0.57
    scenes
    0.52
     Vign
    0.52
    Scenes
    0.51
    场景
    0.50
     scenario
    0.50
     scenes
    0.49
     scena
    0.49
    Act Density 0.018%

    No Known Activations