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
    みます
    0.44
    °,
    0.43
    います
    0.38
     voglio
    0.38
    °.
    0.38
     pero
    0.37
    hmC
    0.37
    ,,
    0.37
    /:
    0.37
    mm
    0.36
    POSITIVE LOGITS
     upang
    0.59
     acknowledging
    0.53
     responding
    0.48
     merely
    0.48
     fossero
    0.46
     كانت
    0.45
    Somos
    0.45
    Để
    0.45
     thoſe
    0.45
     আমরা
    0.45
    Act Density 0.007%

    No Known Activations