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

    Neuronpedia

    INDEX
    Explanations

    Would you like me to:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Khi
    0.85
     While
    0.81
     When
    0.80
    Always
    0.78
     Always
    0.78
     Whereas
    0.78
     вышел
    0.77
     Clos
    0.76
     Please
    0.75
     消費
    0.75
    POSITIVE LOGITS
     there
    1.07
    there
    0.85
     imagining
    0.85
     inventing
    0.83
     uttering
    0.79
     spotting
    0.77
     might
    0.76
     visualizing
    0.75
     thats
    0.75
     वहां
    0.73
    Act Density 0.057%

    No Known Activations