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

    Neuronpedia

    INDEX
    Explanations

    and or listing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TAMBÉM
    -1.18
     also
    -1.16
     также
    -1.13
     também
    -1.10
     OGSÅ
    -1.06
     myös
    -1.01
     cũng
    -0.97
    任何人
    -0.97
     &
    -0.96
    剱
    -0.96
    POSITIVE LOGITS
    过来的
    1.09
    Bibliografie
    1.09
    Fonto
    1.03
    写真を
    0.98
    »-
    0.97
    cising
    0.97
    titudine
    0.96
    íssima
    0.94
    usaha
    0.93
    ktora
    0.90
    Act Density 0.038%

    No Known Activations