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

    Neuronpedia

    INDEX
    Explanations

    system commands and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rocessor
    0.33
    appliqu
    0.33
    your
    0.32
    𒁁
    0.31
     FLOR
    0.31
    ণ্ডের
    0.31
     egent
    0.31
     vocês
    0.30
     eigenlijk
    0.30
     dritten
    0.30
    POSITIVE LOGITS
     તેમને
    0.25
     此
    0.25
     また
    0.24
    -
    0.24
     पुरा
    0.24
    ầm
    0.24
    了一
    0.23
     आया
    0.23
    _
    0.23
     これ
    0.23
    Act Density 0.173%

    No Known Activations