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

    Neuronpedia

    INDEX
    Explanations

    blank space

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    アップ
    -0.07
    .message
    -0.07
     Later
    -0.07
    자인
    -0.06
    discord
    -0.06
    ость
    -0.06
     Vig
    -0.06
     language
    -0.06
    егра
    -0.06
    辞
    -0.06
    POSITIVE LOGITS
    ​
    0.09
     ​
    0.08
     erot
    0.07
    ​​
    0.06
    фіка
    0.06
    BMW
    0.06
    .linkedin
    0.06
     Executors
    0.06
    0.06
    arranty
    0.06
    Act Density 0.002%

    No Known Activations