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

    Neuronpedia

    INDEX
    Explanations

    python slicing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鲟
    0.79
     think
    0.78
     afirmar
    0.78
    +}$,
    0.77
    此次
    0.76
     etmiş
    0.76
    GLFW
    0.76
    本次
    0.75
     calificaciones
    0.75
    nextSend
    0.74
    POSITIVE LOGITS
    [:
    1.17
    slice
    1.15
    [:-
    1.12
    ][:
    1.05
    '][:
    1.03
    Slice
    0.95
     slice
    0.95
     slicing
    0.89
    前
    0.84
     Slice
    0.84
    Act Density 0.155%

    No Known Activations