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

    Neuronpedia

    INDEX
    Explanations

    f

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     বি�
    -0.09
    िल्लो
    -0.08
    াত্র
    -0.07
     Jair
    -0.07
    очке
    -0.07
     Monarch
    -0.07
     TED
    -0.07
    ಿಲ್ಲ
    -0.07
     instructional
    -0.07
    ाँच
    -0.07
    POSITIVE LOGITS
    }")↵
    0.08
     masked
    0.08
     lá
    0.07
     surely
    0.07
     cham
    0.07
     Ago
    0.07
    patched
    0.07
     gums
    0.07
     wagen
    0.07
     aliados
    0.07
    Act Density 0.002%

    No Known Activations