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

    Neuronpedia

    INDEX
    Explanations

    ethical constraints and guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    1.07
    }$\\
    0.86
    }-
    0.82
    u
    0.78
    in
    0.78
    sparsity
    0.76
    л
    0.74
    sembling
    0.73
    गेशन
    0.72
     malt
    0.72
    POSITIVE LOGITS
    П
    0.93
     ограничењима
    0.92
    ราะห์
    0.92
    ی
    0.88
     permeates
    0.87
     withstand
    0.86
    ově
    0.84
    یہ
    0.84
     refuted
    0.82
     equated
    0.82
    Act Density 0.418%

    No Known Activations