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

    Neuronpedia

    INDEX
    Explanations

    However, I

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ആദ്യം
    0.93
     eerst
    0.90
     avete
    0.89
     tenté
    0.87
     প্রথমেই
    0.85
     Nhưng
    0.85
     však
    0.84
     ljudi
    0.84
     کدام
    0.83
    gå
    0.82
    POSITIVE LOGITS
    Also
    1.02
    Note
    1.01
    Furthermore
    0.98
    또한
    0.97
     Note
    0.93
    Similarly
    0.92
    Additionally
    0.85
    Because
    0.83
     note
    0.83
    Moreover
    0.82
    Act Density 0.038%

    No Known Activations