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

    Neuronpedia

    INDEX
    Explanations

    units like month, day, kg, mol

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ى
    0.73
     mises
    0.71
    u
    0.69
    ../../../
    0.68
    the
    0.66
    有可能
    0.66
     nombr
    0.66
    మారు
    0.64
     aventure
    0.64
     dave
    0.63
    POSITIVE LOGITS
     in
    0.77
    的
    0.70
    ς
    0.68
     for
    0.65
     of
    0.64
     poiché
    0.61
    of
    0.60
    ellä
    0.60
    ati
    0.59
    ials
    0.59
    Act Density 0.116%

    No Known Activations