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

    Neuronpedia

    INDEX
    Explanations

    academic introductions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     additionally
    -0.09
     chaise
    -0.08
    Concat
    -0.08
    Contained
    -0.08
    JET
    -0.08
     scared
    -0.08
    Fil
    -0.08
    Ę
    -0.08
     dadurch
    -0.07
     Concierge
    -0.07
    POSITIVE LOGITS
    近年来
    0.10
     என்பது
    0.09
     tegenwoordig
    0.09
     hallmark
    0.09
    യില്
    0.08
    越来越
    0.08
     يُ
    0.08
     undeniably
    0.08
     عبارة
    0.08
     undoubtedly
    0.07
    Act Density 0.119%

    No Known Activations