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

    Neuronpedia

    INDEX
    Explanations

    package dependencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     waterfowl
    0.50
     goldfish
    0.50
    溶液
    0.50
     жидко
    0.50
     सॉल्यूशन
    0.49
     banknote
    0.49
     물질
    0.48
     मछली
    0.48
    रुण
    0.48
    Emerald
    0.48
    POSITIVE LOGITS
    as
    0.78
    in
    0.69
    an
    0.64
    npm
    0.62
    umd
    0.55
    et
    0.54
    ie
    0.53
    um
    0.51
    ett
    0.51
    at
    0.51
    Act Density 0.033%

    No Known Activations