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

    Neuronpedia

    INDEX
    Explanations

    hygiene and denied trauma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /(
    1.41
    loan
    1.38
     vx
    1.35
    Bep
    1.33
     ordinal
    1.32
    rox
    1.32
     Pb
    1.31
    ipos
    1.31
     transference
    1.30
    /_
    1.29
    POSITIVE LOGITS
    しよう
    1.17
    的話
    1.12
    ために
    1.10
    に
    1.07
    에
    1.06
    価値
    1.04
    っ
    1.03
    カッコ
    1.03
    ا
    1.02
    風
    0.99
    Act Density 0.001%

    No Known Activations