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

    Neuronpedia

    INDEX
    Explanations

    operations to perform

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ث
    0.46
     boroughs
    0.43
    요일
    0.43
    怅
    0.42
     karma
    0.42
     ό
    0.41
     ambit
    0.41
     habitantes
    0.41
     inwoners
    0.41
     жители
    0.41
    POSITIVE LOGITS
    inch
    0.45
    fusion
    0.44
     transmits
    0.43
    你要
    0.41
     publishes
    0.41
     transcribe
    0.41
    switch
    0.41
    body
    0.40
    with
    0.40
    pump
    0.40
    Act Density 0.001%

    No Known Activations