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

    Neuronpedia

    INDEX
    Explanations

    things to avoid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Isi
    0.52
    ிறது
    0.52
    ிருந்தது
    0.52
     Sicilian
    0.49
     Bolog
    0.46
     lluvia
    0.46
    🥲
    0.46
     Natasha
    0.46
    ianSpace
    0.45
    فی
    0.45
    POSITIVE LOGITS
    Votes
    0.46
    函
    0.46
    posals
    0.46
    FORMANCE
    0.43
    ajte
    0.40
    পোষ
    0.40
     ট
    0.40
     Arrangement
    0.38
    ндарт
    0.38
    करिता
    0.38
    Act Density 0.001%

    No Known Activations