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

    Neuronpedia

    INDEX
    Explanations

    situational awareness and colors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Alberta
    0.45
    North
    0.45
    News
    0.41
    Centre
    0.40
    Center
    0.40
    '
    0.40
     lét
    0.39
    வதேச
    0.38
    Por
    0.38
    狰
    0.38
    POSITIVE LOGITS
     vok
    0.42
     glu
    0.41
     väx
    0.41
     vikt
    0.40
    ાલુ
    0.39
     সংযুক্ত
    0.39
     জাহাজ
    0.38
     rezat
    0.38
     vadanti
    0.38
     otvore
    0.38
    Act Density 0.000%

    No Known Activations