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

    Neuronpedia

    INDEX
    Explanations

    places and objects with descriptive context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     So
    0.54
     niin
    0.54
    !=
    0.52
     כך
    0.52
     njeg
    0.51
     confirmer
    0.51
     større
    0.51
    So
    0.51
     autre
    0.51
     daar
    0.51
    POSITIVE LOGITS
    dengan
    0.71
    Dengan
    0.64
     with
    0.61
     Sherman
    0.61
     bialgebras
    0.59
     Epstein
    0.58
     dengan
    0.57
    VICIO
    0.56
    issner
    0.56
    மம்
    0.56
    Act Density 0.308%

    No Known Activations