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

    Neuronpedia

    INDEX
    Explanations

    or a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Orders
    0.44
     колле
    0.38
    ຄ
    0.37
    сподар
    0.37
     பண்டைய
    0.36
    ipfs
    0.36
     Bestell
    0.36
    पढ़
    0.36
    ур
    0.36
     ప్రభుత్వ
    0.36
    POSITIVE LOGITS
     dolu
    0.41
     Beacon
    0.39
     fier
    0.39
     rbind
    0.38
     coaction
    0.38
     Reset
    0.38
     update
    0.37
     clean
    0.36
    فك
    0.36
     svim
    0.36
    Act Density 0.000%

    No Known Activations