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

    Neuronpedia

    INDEX
    Explanations

    heavily

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ucional
    0.44
    ху
    0.42
    শুক্রবার
    0.41
    amanya
    0.41
    ோவின்
    0.40
    vindos
    0.39
    onego
    0.38
    फेक्शन
    0.38
     gxh
    0.38
    harma
    0.38
    POSITIVE LOGITS
    AVY
    0.72
    aving
    0.70
    avier
    0.70
    mming
    0.67
    uristic
    0.66
    lla
    0.62
    isenberg
    0.59
    aping
    0.58
    lical
    0.57
    athy
    0.57
    Act Density 0.020%

    No Known Activations