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

    Neuronpedia

    INDEX
    Explanations

    pre- post- prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Stem
    0.50
     stem
    0.46
    stem
    0.46
     Stem
    0.45
    STEM
    0.42
     stems
    0.42
    Expert
    0.41
    expert
    0.41
    exponent
    0.41
    䀘
    0.41
    POSITIVE LOGITS
     deodor
    0.44
     costado
    0.42
     enhancing
    0.42
     ಹಲವಾರು
    0.42
     educating
    0.41
     Deputies
    0.41
     enam
    0.40
     худож
    0.40
     वायू
    0.39
     interacting
    0.39
    Act Density 0.000%

    No Known Activations