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

    Neuronpedia

    INDEX
    Explanations

    steam, fog, vapor, clouds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اً
    3.20
    𝗴
    3.00
    𝗿
    2.92
    𝘀
    2.91
    ın
    2.88
    𝗼
    2.85
    ி
    2.84
    ра
    2.84
    𝗹
    2.78
    iada
    2.76
    POSITIVE LOGITS
     tais
    3.14
    ت
    3.08
    3.08
    Cllr
    2.94
    t
    2.92
     exalted
    2.85
    л
    2.84
     dignitaries
    2.80
    માં
    2.79
     gfx
    2.74
    Act Density 0.134%

    No Known Activations