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

    Neuronpedia

    INDEX
    Explanations

    Reflect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    serve
    -0.07
     şar
    -0.06
     Something
    -0.06
     điều
    -0.06
     Với
    -0.06
     nắm
    -0.06
    _dep
    -0.06
     prosper
    -0.06
     结
    -0.06
     restaur
    -0.06
    POSITIVE LOGITS
     Sex
    0.07
    国際
    0.06
    ораз
    0.06
    ifestyles
    0.06
     supplementation
    0.06
    stdin
    0.06
    áf
    0.06
    .Escape
    0.06
    GetProcAddress
    0.06
    的时候
    0.06
    Act Density 0.097%

    No Known Activations