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

    Neuronpedia

    INDEX
    Explanations

    DOI identifier prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    detail
    0.40
     embrace
    0.39
    Pract
    0.37
    ైన
    0.36
    дру
    0.36
    total
    0.35
     refinement
    0.35
     simulating
    0.34
     pretend
    0.34
    flash
    0.34
    POSITIVE LOGITS
     conferma
    0.42
     пользователя
    0.42
     मर्
    0.42
     نمبر
    0.40
     vodi
    0.40
    كيت
    0.40
    മേ
    0.38
     Saves
    0.38
     noma
    0.38
     chante
    0.37
    Act Density 0.000%

    No Known Activations