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

    Neuronpedia

    INDEX
    Explanations

    overall risk or volatility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rivol
    0.50
     prenda
    0.47
     mă
    0.45
     presenta
    0.45
     it
    0.44
     desag
    0.43
     produc
    0.43
     conn
    0.42
     tels
    0.42
     later
    0.42
    POSITIVE LOGITS
    assapi
    0.58
    EnglishMarks
    0.54
     прошло
    0.47
    š
    0.47
    ታት
    0.46
    ಪಟ್ಟ
    0.46
    citations
    0.46
    punch
    0.45
     ყველა
    0.45
    ianthus
    0.45
    Act Density 0.001%

    No Known Activations