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

    Neuronpedia

    INDEX
    Explanations

    FF

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     certo
    0.59
     quarters
    0.58
     pal
    0.55
     праз
    0.55
     MIM
    0.54
     IMA
    0.52
     mout
    0.52
     cierto
    0.51
     fick
    0.51
     estando
    0.51
    POSITIVE LOGITS
    iciency
    0.93
    iculty
    0.86
    odils
    0.76
    mpeg
    0.74
    ords
    0.71
    ord
    0.70
    icient
    0.69
    eredReader
    0.69
    raff
    0.69
    oon
    0.69
    Act Density 0.024%

    No Known Activations