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

    Neuronpedia

    INDEX
    Explanations

    HTML line breaks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dành
    -0.06
    提供
    -0.06
     oli
    -0.06
    ROUP
    -0.06
     nal
    -0.06
     Happ
    -0.06
     Gov
    -0.06
     ANAL
    -0.06
    вана
    -0.06
    ("${
    -0.06
    POSITIVE LOGITS
    thon
    0.07
    micro
    0.06
    _micro
    0.06
    byt
    0.06
    worker
    0.06
    _
↵
↵
    0.06
     ceilings
    0.06
     přem
    0.06
    agi
    0.06
    jo
    0.06
    Act Density 0.007%

    No Known Activations