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

    Neuronpedia

    INDEX
    Explanations

    posters and flyers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oxidation
    0.40
     oxid
    0.39
     inbound
    0.39
     XOR
    0.38
     arbit
    0.37
     aws
    0.37
     Keys
    0.37
    ဉ
    0.36
     Oxidation
    0.36
     ship
    0.36
    POSITIVE LOGITS
     posters
    3.28
     poster
    3.08
     Posters
    2.92
    Poster
    2.81
     Poster
    2.80
     पोस्टर
    2.78
    poster
    2.77
     flyers
    2.39
     flyer
    2.28
     banners
    2.06
    Act Density 0.021%

    No Known Activations