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

    Neuronpedia

    INDEX
    Explanations

    as if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     solids
    0.42
    s
    0.39
     vantage
    0.38
     닮
    0.38
     bungalows
    0.38
     and
    0.38
     h
    0.38
     bushes
    0.37
     weird
    0.37
     fits
    0.36
    POSITIVE LOGITS
     expecting
    0.49
     buscando
    0.47
    当我们
    0.47
    cevam
    0.46
     esperando
    0.45
    ilibus
    0.45
    是我们
    0.44
     Estamos
    0.44
     fueran
    0.44
     procurando
    0.43
    Act Density 0.007%

    No Known Activations