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

    Neuronpedia

    INDEX
    Explanations

    short size quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nitric
    0.42
     料
    0.39
     nitrous
    0.38
     চৌ
    0.38
    windowActionBar
    0.38
     prisoner
    0.38
     Tjiwarl
    0.37
     selfish
    0.37
     eradic
    0.37
     apoptotic
    0.37
    POSITIVE LOGITS
    міст
    0.39
    izzi
    0.37
    ibi
    0.37
     RI
    0.37
     shorter
    0.36
     సు
    0.36
    short
    0.36
    ⵃ
    0.36
    Short
    0.36
    עד
    0.36
    Act Density 0.000%

    No Known Activations