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

    Neuronpedia

    INDEX
    Explanations

    stop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ad
    1.81
    er
    1.64
    ر
    1.36
     presentamos
    1.26
    questa
    1.26
     manfaat
    1.23
    aw
    1.20
    achusetts
    1.20
    quired
    1.19
    ณ์
    1.18
    POSITIVE LOGITS
     codons
    1.47
     bothering
    1.42
     amazement
    1.30
     তবে
    1.28
     совсем
    1.27
    ✷
    1.25
     tog
    1.23
    workflow
    1.23
     desist
    1.23
     fooling
    1.23
    Act Density 0.038%

    No Known Activations