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

    Neuronpedia

    INDEX
    Explanations

    controversy

    np_max-act · gemini-2.0-flash

    The neuron fires on words that signal controversy or sensationalism, like “controversial,” “controversy,” “hyperbolic,” and similar terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     newX
    -0.06
    Ô
    -0.06
     стоя
    -0.06
    /messages
    -0.06
    .visit
    -0.05
     nên
    -0.05
    >';
    -0.05
    像
    -0.05
     Millennials
    -0.05
     jste
    -0.05
    POSITIVE LOGITS
    อพ
    0.06
    /high
    0.06
    .AddRange
    0.06
    grave
    0.06
    alon
    0.06
     artisans
    0.06
     ORD
    0.06
     inspector
    0.06
    .getParent
    0.06
     Lieutenant
    0.06
    Act Density 0.058%

    No Known Activations