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

    Neuronpedia

    INDEX
    Explanations

    text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Liberal
    -0.09
    ResultSet
    -0.07
    _sender
    -0.07
     
    -0.07
    overview
    -0.06
    James
    -0.06
     James
    -0.06
     Zombie
    -0.06
    .loads
    -0.06
    ்
    -0.06
    POSITIVE LOGITS
     niet
    0.06
    Cent
    0.06
    дет
    0.06
     इनक
    0.06
     नई
    0.06
    稳
    0.06
     última
    0.06
     Derm
    0.06
    —with
    0.06
     أما
    0.06
    Act Density 0.133%

    No Known Activations