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

    Neuronpedia

    INDEX
    Explanations

    content moderation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cocktail
    -0.06
    SAM
    -0.06
     dành
    -0.06
    '].
    -0.06
     ま
    -0.06
     Panda
    -0.06
    _Global
    -0.06
     Βα
    -0.06
    404
    -0.06
     szy
    -0.06
    POSITIVE LOGITS
     complic
    0.07
     بازی
    0.07
     사진
    0.06
    sport
    0.06
    TERM
    0.06
     रक
    0.06
     �
    0.06
     nedost
    0.06
    stit
    0.06
    -final
    0.06
    Act Density 0.040%

    No Known Activations