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

    Neuronpedia

    INDEX
    Explanations

    buffalo animal, milk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لي
    1.05
    ig
    1.05
     in
    1.02
     في
    0.91
    ă
    0.88
     மேம்ப
    0.86
    𝐞
    0.86
     activos
    0.85
     pérdidas
    0.85
    ة
    0.83
    POSITIVE LOGITS
    ’
    1.37
    '
    1.31
    -
    1.30
    (
    1.27
     buffalo
    1.16
    ‘
    1.09
    <h4>
    1.02
     Buffalo
    1.02
    '(
    1.01
     bison
    1.01
    Act Density 0.001%

    No Known Activations