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

    Neuronpedia

    INDEX
    Explanations

    acquiring necessary administrative elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Content
    0.42
    リッジ
    0.39
    ostic
    0.38
    ثر
    0.38
    CLion
    0.38
    Sang
    0.37
     कमर
    0.37
    COLL
    0.36
     serviço
    0.36
    crets
    0.36
    POSITIVE LOGITS
     contingent
    0.44
     измерения
    0.42
     measurement
    0.40
    gada
    0.40
     Instructions
    0.39
     measured
    0.38
     measurements
    0.38
     প
    0.38
     불가
    0.37
     dependents
    0.37
    Act Density 0.000%

    No Known Activations