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

    Neuronpedia

    INDEX
    Explanations

    agonal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jat
    -0.08
     الث
    -0.08
     массива
    -0.08
     fasilitas
    -0.08
     tijdelijke
    -0.08
    Temporary
    -0.07
     অব
    -0.07
     হলেও
    -0.07
     Temp
    -0.07
     �
    -0.07
    POSITIVE LOGITS
     safeguard
    0.08
     Syndrome
    0.08
    realm
    0.07
     tid
    0.07
     amus
    0.07
    िया
    0.07
    gram
    0.07
     divertida
    0.07
     jack
    0.07
    orgd
    0.07
    Act Density 0.002%

    No Known Activations