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

    Neuronpedia

    INDEX
    Explanations

    , but, so, then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gives
    0.50
     sortir
    0.47
     vanishes
    0.47
    note
    0.46
     supprimer
    0.46
    Ꮼ
    0.46
     indiquer
    0.45
     lightness
    0.44
    severe
    0.43
     removes
    0.43
    POSITIVE LOGITS
     tecnológicos
    0.45
     Modern
    0.44
    <0xB2>
    0.42
     Tuhan
    0.42
     современные
    0.41
     modernos
    0.40
     Utopia
    0.40
    旕
    0.40
     Fasc
    0.39
    近代
    0.39
    Act Density 0.004%

    No Known Activations