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

    Neuronpedia

    INDEX
    Explanations

    possessive 's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ture
    0.91
    ين
    0.91
    times
    0.90
    t
    0.86
    ان
    0.81
    een
    0.81
    timestamp
    0.80
    nge
    0.79
    trigger
    0.78
    penguin
    0.78
    POSITIVE LOGITS
     rights
    1.02
     gotta
    0.98
     Rights
    0.95
     wages
    0.87
     sake
    0.86
     prerogative
    0.85
     remorse
    0.85
     suffrage
    0.84
     salaries
    0.83
     POV
    0.82
    Act Density 0.060%

    No Known Activations