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

    Neuronpedia

    INDEX
    Explanations

    Laws and regulations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fragt
    -0.08
    stukken
    -0.08
     eigen
    -0.08
    transpose
    -0.08
    ensus
    -0.08
     мост
    -0.07
     RAID
    -0.07
     Singular
    -0.07
     quilting
    -0.07
     Jacob
    -0.07
    POSITIVE LOGITS
    Smoking
    0.14
     vaping
    0.14
     nicotine
    0.14
     smoking
    0.13
     addiction
    0.13
    -smoking
    0.13
     cigarette
    0.13
     tobacco
    0.12
     cigarettes
    0.12
     smokers
    0.12
    Act Density 0.043%

    No Known Activations