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

    Neuronpedia

    INDEX
    Explanations

    duvet covers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ed
    0.83
    d
    0.79
    zelfde
    0.68
    every
    0.65
    four
    0.63
    o
    0.62
    dic
    0.61
    set
    0.61
    tend
    0.60
    al
    0.59
    POSITIVE LOGITS
     bolognese
    0.55
     sont
    0.54
     이야기
    0.54
     reprise
    0.54
     congrats
    0.53
     ping
    0.52
     cameras
    0.52
    यची
    0.52
     i
    0.51
     patching
    0.51
    Act Density 0.000%

    No Known Activations