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

    Neuronpedia

    INDEX
    Explanations

    file paths and urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    also
    -1.84
     IBOutlet
    -1.73
    大战
    -1.71
    ranslated
    -1.66
    Also
    -1.60
    いえば
    -1.58
    谕
    -1.53
     also
    -1.51
     myös
    -1.48
    ])),
    -1.46
    POSITIVE LOGITS
     we
    1.85
    !
    1.47
     of
    1.46
    kredit
    1.41
     ถ้า
    1.38
     it
    1.38
    postolic
    1.36
     Banyak
    1.34
     yüzden
    1.31
     whoſe
    1.31
    Act Density 0.061%

    No Known Activations