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

    Neuronpedia

    INDEX
    Explanations

    quoted speech starts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yta
    0.53
     стали
    0.52
    elere
    0.52
     дея
    0.51
    kker
    0.50
     нова
    0.50
    kbar
    0.49
    yyati
    0.49
    ara
    0.49
    thisStudent
    0.48
    POSITIVE LOGITS
     or
    0.64
     be
    0.55
     in
    0.55
     have
    0.54
     species
    0.54
     object
    0.53
     water
    0.52
    </h3>
    0.50
     had
    0.50
     are
    0.49
    Act Density 0.008%

    No Known Activations