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

    Neuronpedia

    INDEX
    Explanations

    no later than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Кто
    0.51
     Usuarios
    0.50
    ަރު
    0.50
     Detalles
    0.50
     perspect
    0.49
     anciens
    0.49
     Tecnología
    0.48
     injure
    0.48
    ва
    0.48
     eterno
    0.48
    POSITIVE LOGITS
    N
    0.62
    oise
    0.57
    tained
    0.54
    iguously
    0.50
    igating
    0.50
    うえ
    0.49
     п
    0.49
     Holder
    0.49
     is
    0.48
    โอ
    0.48
    Act Density 0.000%

    No Known Activations