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

    Neuronpedia

    INDEX
    Explanations

    non-existent route or unrelated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     elucid
    0.33
    逖
    0.33
     सेना
    0.32
    暠
    0.32
    रो
    0.30
     프랑
    0.30
     배열
    0.30
    そういう
    0.30
     좋아
    0.30
    誣
    0.30
    POSITIVE LOGITS
     didn
    0.44
     purchased
    0.38
     wasn
    0.34
     doesn
    0.34
     privately
    0.33
    ’
    0.32
     neither
    0.31
     infrequently
    0.31
     purchase
    0.31
     hasn
    0.31
    Act Density 0.000%

    No Known Activations