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

    Neuronpedia

    INDEX
    Explanations

    code and file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lexport
    -0.07
     fie
    -0.07
    arrings
    -0.07
     ***!↵
    -0.06
    .xls
    -0.06
     Stars
    -0.06
    ậ
    -0.06
     sel
    -0.06
    朋友
    -0.06
    ueue
    -0.06
    POSITIVE LOGITS
     Qin
    0.06
     Gins
    0.06
     GFX
    0.06
    nictvím
    0.06
     أك
    0.06
     vše
    0.06
    _patch
    0.06
    ٬
    0.06
     Lifestyle
    0.06
     criar
    0.06
    Act Density 0.922%

    No Known Activations