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

    Neuronpedia

    INDEX
    Explanations

    scientific/technical domain

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Acting
    -0.07
    jh
    -0.07
     piping
    -0.07
     tion
    -0.07
    读书
    -0.07
     Plant
    -0.07
    تمثل
    -0.07
    Increment
    -0.07
    olor
    -0.07
    /social
    -0.07
    POSITIVE LOGITS
     Hưng
    0.07
    ''.
    0.07
    WK
    0.07
     commanders
    0.07
     System
    0.06
    ILLISECONDS
    0.06
    .guard
    0.06
    医科
    0.06
    มาตร
    0.06
     Mal
    0.06
    Act Density 0.155%

    No Known Activations