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

    Neuronpedia

    INDEX
    Explanations

    far more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ation
    0.46
    ATION
    0.45
    URE
    0.45
     First
    0.43
    िएशन
    0.42
     Circuits
    0.42
     Kill
    0.41
     Mutter
    0.40
    RESS
    0.39
     Jangan
    0.39
    POSITIVE LOGITS
     יותר
    0.54
    훨
    0.50
     outnumbered
    0.46
     more
    0.45
     более
    0.43
     أكثر
    0.42
     propos
    0.42
     უფრო
    0.42
     гораздо
    0.41
     paler
    0.40
    Act Density 0.076%

    No Known Activations