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

    Neuronpedia

    INDEX
    Explanations

    words starting with dest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     демо
    0.46
     couple
    0.44
     Couple
    0.42
     Source
    0.41
     Kumari
    0.41
     Sources
    0.41
     corporate
    0.40
     source
    0.40
     sources
    0.40
     Grid
    0.40
    POSITIVE LOGITS
     Dest
    0.61
    Dest
    0.55
     dest
    0.54
    dest
    0.47
     destin
    0.46
    ïs
    0.42
    DEST
    0.42
     DEST
    0.42
     destinada
    0.39
    Dst
    0.38
    Act Density 0.006%

    No Known Activations