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

    Neuronpedia

    INDEX
    Explanations

    freeing up for strategic work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     government
    0.65
    or
    0.65
     etc
    0.63
    desc
    0.62
     aka
    0.60
     or
    0.59
    government
    0.57
     или
    0.55
    etc
    0.55
    يديو
    0.54
    POSITIVE LOGITS
     subtle
    1.06
     SIGNIFIC
    0.98
     sinnv
    0.97
     soothe
    0.97
     Subtle
    0.96
    බන්ධ
    0.96
    丁寧
    0.95
     delikat
    0.95
    讓
    0.95
     sinnvoll
    0.95
    Act Density 0.002%

    No Known Activations