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

    Neuronpedia

    INDEX
    Explanations

    leading edge innovation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     başkan
    0.36
     byg
    0.34
    ີ
    0.33
     party
    0.33
     tribes
    0.33
     welchem
    0.33
     presid
    0.32
     malef
    0.32
    են
    0.32
     constitue
    0.31
    POSITIVE LOGITS
    ualitas
    0.42
    atasi
    0.41
    ounded
    0.38
    olateral
    0.38
    ol
    0.37
    infrared
    0.37
    et
    0.36
    inse
    0.36
    woven
    0.36
    itation
    0.36
    Act Density 0.074%

    No Known Activations