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

    Neuronpedia

    INDEX
    Explanations

    code snippets/commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     smr
    -0.08
    ىتى
    -0.07
     pendek
    -0.07
     نه
    -0.07
    reiten
    -0.07
    _internal
    -0.07
    Nga
    -0.07
    well
    -0.07
     derivative
    -0.07
     DER
    -0.07
    POSITIVE LOGITS
     считает
    0.09
    님
    0.09
     :::::
    0.08
     오후
    0.08
     aggi
    0.08
    秋
    0.08
     теперь
    0.08
    Breakpoint
    0.08
     coworkers
    0.08
    versations
    0.08
    Act Density 0.005%

    No Known Activations