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

    Neuronpedia

    INDEX
    Explanations

    User interface elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    标
    -0.08
    计
    -0.07
     AKA
    -0.07
     انقلاب
    -0.07
     RNA
    -0.07
     hallmark
    -0.07
     Republicans
    -0.07
     housing
    -0.07
     relatives
    -0.07
    -0.07
    POSITIVE LOGITS
     Sympathy
    0.09
    ப்படுகிறது
    0.09
    Ignoring
    0.08
    되는
    0.08
     ignore
    0.08
     ignor
    0.08
    丘
    0.08
     내가
    0.08
    gifter
    0.08
     ignoring
    0.07
    Act Density 0.000%
    No Known Activations