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

    Neuronpedia

    INDEX
    Explanations

    book titles and topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’।
    0.38
    䢀
    0.36
    捚
    0.36
    旕
    0.34
    峼
    0.33
    গ্ত
    0.33
    嚧
    0.32
    㕶
    0.32
    鿉
    0.32
    贰章
    0.32
    POSITIVE LOGITS
    -
    0.45
    G
    0.36
    V
    0.35
    2
    0.34
    R
    0.34
    f
    0.33
    v
    0.33
    L
    0.33
    sp
    0.32
     '
    0.32
    Act Density 0.001%

    No Known Activations