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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ベ
    -0.06
    looks
    -0.06
    に対
    -0.06
     إل
    -0.06
     Payne
    -0.06
     ศ
    -0.06
     واست
    -0.06
     правильно
    -0.06
    ''
    -0.06
     Hayden
    -0.06
    POSITIVE LOGITS
     sterling
    0.07
     calidad
    0.06
    �
    0.06
     آهنگ
    0.06
    ा-
    0.06
     frem
    0.06
    陆
    0.06
    /REC
    0.06
    Answer
    0.06
     fren
    0.06
    Act Density 0.039%

    No Known Activations