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

    Neuronpedia

    INDEX
    Explanations

    Git version control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     italy
    0.46
     méd
    0.42
     Италии
    0.41
     gi
    0.40
     italia
    0.39
     terce
    0.39
     regno
    0.38
     refuge
    0.38
     Gi
    0.38
     Staples
    0.37
    POSITIVE LOGITS
    Sche
    0.46
    ೆಯನ್ನು
    0.41
     ENS
    0.39
    ENS
    0.38
    Liter
    0.38
    Approved
    0.37
     sche
    0.36
     schemas
    0.36
     እንዲሁም
    0.36
     schemes
    0.36
    Act Density 0.001%

    No Known Activations