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

    Neuronpedia

    INDEX
    Explanations

    data class definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abama
    0.44
    вань
    0.43
    народ
    0.43
    ීමට
    0.42
    commit
    0.42
    ందుకు
    0.42
     bienvenidas
    0.41
    accordo
    0.41
    durch
    0.41
     ಸಾಮಾ
    0.41
    POSITIVE LOGITS
     পাচ্ছেন
    0.45
     and
    0.43
    ッグ
    0.40
    '
    0.40
     Archim
    0.39
     Elastic
    0.39
     pliable
    0.39
     &
    0.39
     ہیں
    0.38
     AI
    0.38
    Act Density 0.002%

    No Known Activations