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

    Neuronpedia

    INDEX
    Explanations

    platform channel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     руководство
    0.97
    p
    0.94
    ização
    0.90
    isatie
    0.90
     соотно
    0.89
    бычно
    0.88
     более
    0.88
    osť
    0.86
     искусство
    0.86
    idencia
    0.86
    POSITIVE LOGITS
     breeze
    0.92
     chariot
    0.89
     definitely
    0.87
    ନ୍ଦ
    0.85
    єю
    0.85
     roar
    0.84
     concerts
    0.84
     qRT
    0.83
     R
    0.82
     professions
    0.81
    Act Density 0.001%

    No Known Activations