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

    Neuronpedia

    INDEX
    Explanations

    URLs and academic links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Redmi
    0.83
     sold
    0.81
     sign
    0.80
     portfolio
    0.79
     Rainbow
    0.77
     shouts
    0.77
     товары
    0.77
     compan
    0.77
     holiday
    0.76
     company
    0.75
    POSITIVE LOGITS
    doi
    1.52
    DOI
    1.17
     doi
    1.05
    ncbi
    1.01
    https
    0.84
    pdf
    0.81
    ISBN
    0.80
     DOI
    0.80
    文献
    0.80
    javase
    0.79
    Act Density 0.029%

    No Known Activations