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

    Neuronpedia

    INDEX
    Explanations

    code and server data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    구
    -0.06
    #!/
    -0.06
    Nano
    -0.06
     Agricult
    -0.06
    dbl
    -0.06
     Gem
    -0.05
    Old
    -0.05
    ��
    -0.05
    .space
    -0.05
    Produto
    -0.05
    POSITIVE LOGITS
    Actual
    0.07
     Science
    0.07
     deterrent
    0.07
     собой
    0.06
     Єв
    0.06
    Words
    0.06
    ผ
    0.06
    ธาน
    0.06
    ागत
    0.06
    خانه
    0.06
    Act Density 0.006%

    No Known Activations