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

    Neuronpedia

    INDEX
    Explanations

    MEMORANDUM headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    poz
    0.49
    little
    0.46
    King
    0.46
     अवशेष
    0.45
    vre
    0.45
    Cut
    0.45
    Gr
    0.45
    V
    0.44
    Belgium
    0.44
    Br
    0.44
    POSITIVE LOGITS
     toga
    0.46
     briefcase
    0.45
    ји
    0.43
     tost
    0.43
     gooey
    0.42
     bây
    0.42
     이러한
    0.41
     всички
    0.40
     Ettha
    0.40
     destinations
    0.40
    Act Density 0.025%

    No Known Activations