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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—especially floating‐point values and percentages—that represent measured results or statistical figures in scientific text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Genesis
    -0.07
     Sunday
    -0.06
     Trident
    -0.06
     APP
    -0.06
    endale
    -0.06
     fists
    -0.06
    DBC
    -0.06
    ric
    -0.06
     thirst
    -0.06
    dorf
    -0.06
    POSITIVE LOGITS
    ยะ
    0.06
    TableModel
    0.06
    _optimizer
    0.06
    _altern
    0.06
     newcom
    0.06
     imageNamed
    0.06
     setBackground
    0.06
    .wp
    0.06
     huku
    0.06
     grátis
    0.06
    Act Density 0.114%

    No Known Activations