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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Era
    -0.07
     ner
    -0.07
    _plugin
    -0.07
     inh
    -0.07
    IFY
    -0.06
     Knife
    -0.06
    אופן
    -0.06
     inexpensive
    -0.06
     OPP
    -0.06
    _VERIFY
    -0.06
    POSITIVE LOGITS
     trajectories
    0.07
    .ArgumentParser
    0.07
    أسب
    0.07
    (&
    0.06
     الخارج
    0.06
    brates
    0.06
    Numer
    0.06
    Cur
    0.06
    让
    0.06
    opensource
    0.06
    Act Density 0.004%

    No Known Activations