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

    Neuronpedia

    INDEX
    Explanations

    service offerings/requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dropout
    -0.07
     STREAM
    -0.06
    codile
    -0.06
     publishing
    -0.06
     рекомен
    -0.06
    esture
    -0.06
    -trigger
    -0.06
    MULT
    -0.06
    십시오
    -0.06
    enemy
    -0.06
    POSITIVE LOGITS
     福
    0.06
     дотрим
    0.06
    ُوا
    0.06
     '''
↵
    0.06
     против
    0.06
     ill
    0.06
    ?”
    0.06
     ThemeData
    0.06
    (...
    0.06
    �
    0.06
    Act Density 0.008%

    No Known Activations