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

    Neuronpedia

    INDEX
    Explanations

    Halo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     violin
    -0.08
    주세요
    -0.07
     IEnumerable
    -0.07
     veggies
    -0.06
     Song
    -0.06
     Ross
    -0.06
     Ấn
    -0.06
     Brick
    -0.06
    aver
    -0.06
     girl
    -0.06
    POSITIVE LOGITS
     Hal
    0.13
     Halo
    0.12
     hal
    0.11
     halo
    0.11
     HAL
    0.11
    Hal
    0.10
    hal
    0.10
    HAL
    0.09
    	HAL
    0.08
     Janet
    0.07
    Act Density 0.005%

    No Known Activations