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

    Neuronpedia

    INDEX
    Explanations

    technical documentation and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \
    0.65
    ):
    0.54
     \
    0.47
    order
    0.47
    $
    0.46
     italic
    0.46
     ORDER
    0.46
    تبر
    0.44
     SLAs
    0.44
    מ
    0.44
    POSITIVE LOGITS
    cesa
    0.51
     Xuân
    0.51
    ভৃতি
    0.49
    acat
    0.49
    kinase
    0.48
    ക്കളുടെ
    0.48
     composição
    0.47
     stø
    0.47
    慈善
    0.47
    IG
    0.46
    Act Density 0.001%

    No Known Activations