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

    Neuronpedia

    INDEX
    Explanations

    foreign language words and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    currency
    0.52
    sty
    0.49
    ma
    0.47
    cad
    0.47
    egar
    0.46
    an
    0.45
    cha
    0.44
    avar
    0.44
    ear
    0.44
    ham
    0.44
    POSITIVE LOGITS
    Кто
    0.60
     Coronado
    0.53
     Schreiben
    0.53
     Luiz
    0.52
     Consid
    0.51
     Contest
    0.50
     Ravi
    0.49
     Neuen
    0.49
    公示
    0.48
    媺
    0.48
    Act Density 0.001%

    No Known Activations