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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tensor
    -0.07
    	ss
    -0.07
    (js
    -0.07
    泔
    -0.07
    *cos
    -0.07
    𝗛
    -0.07
    guess
    -0.07
    Coffee
    -0.07
    ManagerInterface
    -0.07
    ValueGenerationStrategy
    -0.06
    POSITIVE LOGITS
     Tân
    0.07
    _EXECUTE
    0.07
    UILabel
    0.07
    qp
    0.07
     Semi
    0.07
     multin
    0.07
     '\''
    0.07
    ➚
    0.07
    ecute
    0.07
     genitals
    0.06
    Act Density 0.125%

    No Known Activations