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

    Neuronpedia

    INDEX
    Explanations

    models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intro
    -0.07
     Uk
    -0.07
    HttpContext
    -0.06
    .ncbi
    -0.06
    ',{
    -0.06
     crt
    -0.06
    aston
    -0.06
     Netz
    -0.06
     refuge
    -0.06
     OV
    -0.06
    POSITIVE LOGITS
     فور
    0.06
    _REAL
    0.06
    参照
    0.06
     reclaim
    0.06
    تا
    0.06
     นาง
    0.06
    ':
↵
    0.06
     ты
    0.06
     ici
    0.05
    according
    0.05
    Act Density 0.000%

    No Known Activations