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

    Neuronpedia

    INDEX
    Explanations

    zip archive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ullivan
    0.38
    麻烦
    0.37
    刺激
    0.37
    ・・・・
    0.37
    ney
    0.36
    udsman
    0.35
    Range
    0.35
     collapsing
    0.35
     disliked
    0.35
     Nobody
    0.35
    POSITIVE LOGITS
    രിയ
    0.43
     proport
    0.39
    RAMM
    0.39
    feet
    0.38
     skladu
    0.38
     deut
    0.37
     elegant
    0.37
    लेषण
    0.36
     preto
    0.36
     methylated
    0.36
    Act Density 0.000%

    No Known Activations