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

    Neuronpedia

    INDEX
    Explanations

    Markup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Collect
    -0.07
    awa
    -0.07
     deterior
    -0.07
    品質
    -0.07
    ProcAddress
    -0.07
    _intent
    -0.07
    -not
    -0.06
     Wear
    -0.06
     repost
    -0.06
    Painter
    -0.06
    POSITIVE LOGITS
    umba
    0.08
    电商平台
    0.07
     ozone
    0.07
    🗓
    0.07
     차
    0.07
    -lined
    0.07
     logic
    0.07
     $_
    0.07
     housing
    0.07
    汪
    0.07
    Act Density 0.394%

    No Known Activations