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

    Neuronpedia

    INDEX
    Explanations

    create custom documentation and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     выбран
    0.40
    Newly
    0.36
     newly
    0.35
     yapılan
    0.34
     Newly
    0.32
     প্রসঙ্গ
    0.32
     найден
    0.32
     diagonalization
    0.32
    iquity
    0.32
    Downloaded
    0.31
    POSITIVE LOGITS
     custom
    0.61
     bespoke
    0.57
     customized
    0.52
     workable
    0.49
     personalizados
    0.48
     personalized
    0.46
    カスタム
    0.46
     playlists
    0.46
     personalizado
    0.46
     personalizada
    0.45
    Act Density 0.131%

    No Known Activations