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

    Neuronpedia

    INDEX
    Explanations

    Would

    np_max-act · gemini-2.0-flash

    This neuron activates on words and phrases that introduce or refer to legislative proposals and bills (e.g., “Proposal,” “Bill,” “Legislation,” “would,” “introduced,” “Would”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _tags
    -0.07
    .functional
    -0.07
    _reviews
    -0.07
    _definition
    -0.06
     Problems
    -0.06
     subsets
    -0.06
     Ngh
    -0.06
    )=>{↵
    -0.06
     Validates
    -0.06
    Reserved
    -0.06
    POSITIVE LOGITS
     Glass
    0.07
     DEL
    0.07
    403
    0.07
     친
    0.07
     gazet
    0.06
    ısında
    0.06
     nama
    0.06
    Gear
    0.06
    觀
    0.06
    親
    0.06
    Act Density 0.016%

    No Known Activations