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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _chain
    -0.07
    )'),↵
    -0.06
    Rec
    -0.06
    fra
    -0.06
    煙
    -0.06
     stretch
    -0.06
     discre
    -0.06
    ả
    -0.06
    wright
    -0.06
     Compute
    -0.06
    POSITIVE LOGITS
    ebilirsiniz
    0.07
    句
    0.06
     metav
    0.06
    sPid
    0.06
    :false
    0.06
    Neil
    0.06
     milyon
    0.06
     ";"
    0.06
     Про
    0.06
    COOKIE
    0.06
    Act Density 0.080%

    No Known Activations