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

    Neuronpedia

    INDEX
    Explanations

    Learning instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ges
    -0.08
     speeches
    -0.08
     Journalism
    -0.07
     제거
    -0.07
     erad
    -0.07
     Größen
    -0.07
     प्रत्य
    -0.07
    187
    -0.07
     التحر
    -0.07
     journalism
    -0.07
    POSITIVE LOGITS
    оритет
    0.08
     passie
    0.08
     paixão
    0.08
    quelize
    0.08
     unidos
    0.08
    �
    0.08
     орны
    0.08
    ણી
    0.08
     konkurr
    0.07
     pancreas
    0.07
    Act Density 0.001%

    No Known Activations