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

    Neuronpedia

    INDEX
    Explanations

    Replace with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     some
    1.37
     five
    1.33
     old
    1.30
     many
    1.30
     two
    1.24
     six
    1.23
     microbes
    1.22
     seven
    1.21
     first
    1.20
     small
    1.20
    POSITIVE LOGITS
    utilisateur
    1.36
    abilità
    1.35
    extrémité
    1.34
    umetric
    1.25
    améliorer
    1.22
    ermanfaat
    1.17
    événement
    1.16
    ável
    1.16
    )،
    1.14
     обеспечивает
    1.14
    Act Density 0.868%

    No Known Activations