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

    Neuronpedia

    INDEX
    Explanations

    answering questions about a topic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tender
    -0.07
     SqlConnection
    -0.07
    ollapsed
    -0.06
    worked
    -0.06
    <Tuple
    -0.06
    Shader
    -0.06
     Tender
    -0.06
     tmp
    -0.06
    Bin
    -0.06
    -work
    -0.06
    POSITIVE LOGITS
    て
    0.07
    _angles
    0.07
    后台
    0.07
     relu
    0.07
    低成本
    0.07
    代表性
    0.07
     réfé
    0.07
    �
    0.07
     dismiss
    0.06
     coeffs
    0.06
    Act Density 0.001%

    No Known Activations