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

    Neuronpedia

    INDEX
    Explanations

    to be perceived

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ότητας
    0.61
    ostiene
    0.61
    勾
    0.58
     ол
    0.55
    ో
    0.54
    迠
    0.54
    ertime
    0.54
    BRA
    0.52
    igamma
    0.52
     통해
    0.51
    POSITIVE LOGITS
     [
    0.55
     live
    0.54
     মার্ক
    0.52
    ['
    0.52
    ment
    0.51
     milling
    0.51
     hub
    0.50
     ['
    0.50
     inmates
    0.49
    ham
    0.48
    Act Density 0.000%

    No Known Activations