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

    Neuronpedia

    INDEX
    Explanations

    asking for tone and context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     *
    0.73
    ?"
    0.72
     what
    0.72
     arouse
    0.70
     `
    0.67
     au
    0.67
     দিয়েই
    0.66
    what
    0.65
     merciful
    0.60
     Amenities
    0.60
    POSITIVE LOGITS
     الشركات
    0.94
    .//
    0.92
     húmed
    0.86
    .])
    0.85
     bedrijven
    0.84
     اخرى
    0.83
     النقطه
    0.82
    ฏ
    0.82
     kanggo
    0.81
    În
    0.81
    Act Density 0.031%

    No Known Activations