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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulsion
    -0.07
    ateway
    -0.06
    uddy
    -0.06
    енность
    -0.06
    код
    -0.06
    combo
    -0.06
    factory
    -0.06
    _nc
    -0.06
     threw
    -0.06
    ät
    -0.06
    POSITIVE LOGITS
     Carnegie
    0.06
    #\
    0.06
     cref
    0.06
     acept
    0.06
    子の
    0.06
    'nde
    0.06
     RR
    0.06
     administrative
    0.06
     '{}'
    0.06
     В
    0.06
    Act Density 0.153%

    No Known Activations