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

    Neuronpedia

    INDEX
    Explanations

    legal and formal rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     increíble
    1.51
     veldig
    1.51
     incroyable
    1.46
     unglaublich
    1.45
     divertido
    1.35
     Muitos
    1.32
     racconta
    1.30
     berühm
    1.28
     Leute
    1.26
     Entrenamiento
    1.25
    POSITIVE LOGITS
     duly
    1.12
     pursuant
    1.06
     conformément
    0.99
     prescribed
    0.98
     legally
    0.98
     ascertain
    0.94
     prescribe
    0.92
     lawfully
    0.91
     technical
    0.91
     determined
    0.86
    Act Density 0.080%

    No Known Activations