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

    Neuronpedia

    INDEX
    Explanations

    bold emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     일반적으로
    0.45
    Recogn
    0.43
    Typically
    0.42
     generically
    0.41
     argued
    0.38
     legislative
    0.38
     searchable
    0.37
     prescribe
    0.37
     valid
    0.37
    çada
    0.36
    POSITIVE LOGITS
    ೋಷ
    0.53
    設備
    0.46
    t
    0.44
     Oxygen
    0.42
     Vendor
    0.42
     Vin
    0.42
    賖
    0.42
     ライン
    0.41
     Tourist
    0.40
    सायन
    0.40
    Act Density 0.005%

    No Known Activations