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

    Neuronpedia

    INDEX
    Explanations

    or rather

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     对于
    1.25
     youtube
    1.23
     但是
    1.15
    এবং
    1.15
     購入
    1.13
    𝗽
    1.11
     않고
    1.09
     由于
    1.09
    youtube
    1.08
    yahoo
    1.07
    POSITIVE LOGITS
    gång
    1.20
    żs
    1.13
     अधिका
    1.10
     broader
    1.08
    ższy
    1.08
    kode
    1.07
    ți
    1.05
    मर्रा
    1.05
    CharCode
    1.03
    ñas
    1.03
    Act Density 0.000%

    No Known Activations