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

    Neuronpedia

    INDEX
    Explanations

    multi-language concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    한다는
    0.45
     হইলেও
    0.45
     geldi
    0.45
    っている
    0.43
    (
    0.43
     inextric
    0.43
    ใน
    0.42
     culminated
    0.41
    ින්
    0.41
     supermarkets
    0.41
    POSITIVE LOGITS
    sphere
    0.50
    সহ
    0.47
    san
    0.47
     наре
    0.47
    cuando
    0.47
    supervised
    0.46
    street
    0.46
    supplier
    0.45
    nament
    0.45
     సాం
    0.45
    Act Density 0.001%

    No Known Activations