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

    Neuronpedia

    INDEX
    Explanations

    programming imports and components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    noindent
    0.44
    scri
    0.42
     legalize
    0.41
    论
    0.40
     уви
    0.39
    ыска
    0.39
    菉
    0.39
    кси
    0.38
     zeigte
    0.37
     дают
    0.37
    POSITIVE LOGITS
     What
    0.46
     Pi
    0.44
    whats
    0.43
    0.42
    users
    0.41
    reducers
    0.41
     About
    0.41
     All
    0.41
     Ale
    0.41
     ep
    0.40
    Act Density 0.000%

    No Known Activations