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

    Neuronpedia

    INDEX
    Explanations

    suppressing information

    np_max-act · gemini-2.0-flash

    The neuron fires on words denoting acts of suppression or silencing (e.g., “crush,” “suppress,” “conceal,” “silencing”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _bit
    -0.07
    效
    -0.06
    ','',
    -0.06
    Expired
    -0.06
     以
    -0.06
    serde
    -0.06
     toItem
    -0.06
    .branch
    -0.06
    ValuePair
    -0.06
     дис
    -0.06
    POSITIVE LOGITS
    fx
    0.07
     labels
    0.06
    лению
    0.06
     Veterans
    0.06
    commerce
    0.06
    izen
    0.06
     Prim
    0.06
     dovol
    0.06
     assertion
    0.06
     refrigerator
    0.06
    Act Density 0.020%

    No Known Activations