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

    Neuronpedia

    INDEX
    Explanations

    increasingly prevalent and crucial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     or
    1.75
     или
    1.61
    或
    1.50
     eller
    1.47
     atau
    1.43
     或
    1.39
     oder
    1.39
     அல்லது
    1.38
    /
    1.37
     या
    1.34
    POSITIVE LOGITS
    近年
    1.38
     strives
    1.35
     OEMs
    1.32
     leverages
    1.31
    érons
    1.30
     profitability
    1.29
     través
    1.26
     underpin
    1.26
     다양한
    1.25
    面临
    1.25
    Act Density 0.273%

    No Known Activations