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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -transitional
    -0.07
    passport
    -0.07
     deutsch
    -0.07
    argest
    -0.07
    travel
    -0.07
     quo
    -0.07
     Defendant
    -0.07
    živ
    -0.06
     prescribed
    -0.06
    щё
    -0.06
    POSITIVE LOGITS
    ,node
    0.07
    -transform
    0.06
    32
    0.06
    naz
    0.06
    TER
    0.06
    (main
    0.06
     }];↵↵
    0.06
     Agenda
    0.06
    :',
    0.06
     Tou
    0.06
    Act Density 0.000%

    No Known Activations