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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    asarray
    0.33
     দৃঢ়
    0.32
     submenu
    0.32
     unitary
    0.32
     দৃঢ়
    0.31
     Weib
    0.31
     whiteboard
    0.31
     詳細
    0.31
    ytail
    0.31
    ondata
    0.30
    POSITIVE LOGITS
    映画
    0.42
     famosos
    0.39
     famously
    0.36
     Amerika
    0.36
    סי
    0.35
    穌
    0.34
     horrors
    0.34
    ১৯
    0.34
    Avengers
    0.34
    电影
    0.33
    Act Density 0.028%

    No Known Activations