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

    Neuronpedia

    INDEX
    Explanations

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     multitude
    0.55
     name
    0.53
     perimeter
    0.51
     cornerstone
    0.49
    티
    0.49
    니
    0.48
     wonderland
    0.47
    로
    0.47
    에
    0.47
     segmented
    0.46
    POSITIVE LOGITS
    dzie
    0.70
    )}$.
    0.69
     arabe
    0.68
     jeden
    0.68
     edizione
    0.68
     êtes
    0.67
     rapidement
    0.67
    rzez
    0.67
    amı
    0.66
     mehr
    0.66
    Act Density 0.222%

    No Known Activations