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

    Neuronpedia

    INDEX
    Explanations

    partial word beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reside
    0.31
     lengths
    0.30
     reunion
    0.30
     screens
    0.30
     carnival
    0.30
     usk
    0.30
     departures
    0.29
     sketch
    0.29
     durations
    0.29
     sunglasses
    0.29
    POSITIVE LOGITS
    wenden
    0.44
    ierend
    0.42
    Dieser
    0.42
    CHREIBUNG
    0.41
    Diese
    0.41
    iniert
    0.40
     allgeme
    0.39
    zahlen
    0.38
    Unsere
    0.38
    setzung
    0.38
    Act Density 0.000%

    No Known Activations