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

    Neuronpedia

    INDEX
    Explanations

    SOAP note

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     starved
    0.41
    Scissors
    0.39
     मारी
    0.39
     cowboy
    0.39
     unleashed
    0.39
    universe
    0.38
     особое
    0.38
    󰡔
    0.38
    Splash
    0.37
    untitled
    0.37
    POSITIVE LOGITS
     anzeigen
    0.41
     menampilkan
    0.39
     pie
    0.38
    SOUND
    0.38
     Pies
    0.38
     prep
    0.38
     Yates
    0.38
     pies
    0.36
     wat
    0.36
    マト
    0.36
    Act Density 0.003%

    No Known Activations