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

    Neuronpedia

    INDEX
    Explanations

    Sounds awful, DisplayPort, It was

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ാം
    0.69
     imati
    0.68
    ണ്‍
    0.68
     বুঝ
    0.67
    心中
    0.67
    stay
    0.66
    th
    0.66
    cl
    0.66
    yst
    0.64
    ste
    0.63
    POSITIVE LOGITS
    瀉
    0.75
     organisasi
    0.75
    ご了承ください
    0.69
     transitional
    0.69
     paragraph
    0.68
     μ
    0.68
     행
    0.67
     Paragraph
    0.67
     anthropological
    0.66
     KS
    0.66
    Act Density 0.000%

    No Known Activations