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

    Neuronpedia

    INDEX
    Explanations

    URL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wholesale
    -0.07
    _ATTACHMENT
    -0.07
    "W
    -0.07
    "C
    -0.07
     forEach
    -0.06
    NX
    -0.06
    .tbl
    -0.06
    _FALL
    -0.06
     bitch
    -0.06
     tweaking
    -0.06
    POSITIVE LOGITS
    まり
    0.07
    ...↵↵↵↵
    0.07
    数学
    0.06
     开始
    0.06
     BeautifulSoup
    0.06
     deliber
    0.06
     гориз
    0.06
    Whilst
    0.06
    ivil
    0.06
    rp
    0.06
    Act Density 0.011%

    No Known Activations