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

    Neuronpedia

    INDEX
    Explanations

    company/product names and capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    whom
    0.73
     Sự
    0.54
     ordeal
    0.53
     Whom
    0.51
     whom
    0.51
    epoch
    0.50
    和一个
    0.50
     craze
    0.50
     Đó
    0.50
    Reset
    0.50
    POSITIVE LOGITS
     strives
    1.14
     prides
    1.13
     incorporates
    1.12
     encourages
    1.09
     operates
    1.03
     aspires
    1.03
     telah
    1.02
     recognizes
    1.01
     utilizes
    1.01
     supports
    1.00
    Act Density 0.098%

    No Known Activations