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

    Neuronpedia

    INDEX
    Explanations

    if statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isca
    0.40
    Location
    0.40
    ặt
    0.40
    还好
    0.40
    acje
    0.39
    的話
    0.38
    acja
    0.38
    Ftp
    0.38
    挨
    0.37
    iniai
    0.37
    POSITIVE LOGITS
     inhib
    0.51
     longue
    0.47
     devo
    0.44
     lait
    0.43
     spire
    0.43
    ostrum
    0.43
     sebum
    0.42
     carapace
    0.41
     souris
    0.41
     стрем
    0.41
    Act Density 0.000%

    No Known Activations