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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ver
    -0.08
     closest
    -0.07
    _COOKIE
    -0.07
    js
    -0.07
    _red
    -0.06
     RW
    -0.06
     따라
    -0.06
    edited
    -0.06
    .COM
    -0.06
    query
    -0.06
    POSITIVE LOGITS
    	Application
    0.08
    ﯕ
    0.07
    <tbody
    0.07
    굵
    0.07
    -offsetof
    0.07
    诇
    0.07
    0.07
     gown
    0.07
    엎
    0.07
     Profession
    0.07
    Act Density 0.054%

    No Known Activations