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

    Neuronpedia

    INDEX
    Explanations

    y

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     informant
    -0.07
    aceutical
    -0.07
    Anime
    -0.07
    erne
    -0.07
    authorize
    -0.07
    .cbo
    -0.07
     Ave
    -0.06
     filmes
    -0.06
     Martinez
    -0.06
    ΙΛ
    -0.06
    POSITIVE LOGITS
     этому
    0.07
    Trading
    0.06
     MIN
    0.06
     كنت
    0.06
     scientifically
    0.06
    ่วน
    0.06
    DOCKER
    0.06
     belts
    0.06
     UNIT
    0.06
    Game
    0.06
    Act Density 0.016%

    No Known Activations