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

    Neuronpedia

    INDEX
    Explanations

    the ` ` ` ` code delimiter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sea
    0.30
    ")
    0.30
     ataupun
    0.29
    )\
    0.29
     creating
    0.29
     membuat
    0.29
     There
    0.28
     legitimately
    0.28
     providing
    0.28
     :
    0.28
    POSITIVE LOGITS
     інші
    0.42
     інших
    0.39
    autres
    0.39
    yrıca
    0.39
    其他
    0.37
     andere
    0.37
     други
    0.35
    其他的
    0.35
     другой
    0.35
    ة
    0.35
    Act Density 0.124%

    No Known Activations