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

    Neuronpedia

    INDEX
    Explanations

    generating images automatically

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     orada
    0.43
     mempengaruhi
    0.40
     herkes
    0.39
     junt
    0.38
     anyway
    0.38
    pengaruhi
    0.37
     Hemos
    0.37
     there
    0.37
     My
    0.36
     betroffen
    0.36
    POSITIVE LOGITS
     automatically
    1.03
     instantaneously
    1.02
     자동으로
    0.99
    automatically
    0.98
     instantly
    0.95
     automatisch
    0.92
    自动
    0.91
     automaticamente
    0.91
     automáticamente
    0.90
     स्वचालित
    0.90
    Act Density 0.022%

    No Known Activations