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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating different types of "forms" or classifications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    form of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maternidade
    -0.46
     designers
    -0.45
     aveug
    -0.43
     affari
    -0.43
     exécu
    -0.43
     Moscú
    -0.42
     viime
    -0.42
     réfrig
    -0.42
     kirja
    -0.41
     menak
    -0.41
    POSITIVE LOGITS
    verwijspagina
    0.72
     informée
    0.71
    WriteTagHelper
    0.70
    MigrationBuilder
    0.67
     '\\;'
    0.65
     autorytatywna
    0.65
    NameInMap
    0.65
    0.63
    EnableWeb
    0.63
    AxisAlignment
    0.60
    Act Density 0.022%

    No Known Activations