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

    Neuronpedia

    INDEX
    Explanations

    offering options if asked

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Acuerdo
    0.43
    いたり
    0.42
    যন্ত্র
    0.42
     buồn
    0.42
     edilen
    0.40
    తులు
    0.40
    或者是
    0.40
    하였
    0.39
    lection
    0.39
     सदर
    0.38
    POSITIVE LOGITS
     dozens
    0.44
     pads
    0.43
     ignoreString
    0.42
     सीधे
    0.41
     fles
    0.40
     πλή
    0.40
     downright
    0.39
     একদম
    0.39
     snapshots
    0.39
     కీలక
    0.39
    Act Density 0.007%

    No Known Activations