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

    Neuronpedia

    INDEX
    Explanations

    order

    np_max-act · gemini-2.0-flash

    This neuron doesn’t respond to any tokens—it remains inactive and doesn’t detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Sharper
    -0.07
    スの
    -0.07
     elsewhere
    -0.07
     realization
    -0.06
    SIG
    -0.06
     dijital
    -0.06
     servers
    -0.06
     Liber
    -0.06
     زنان
    -0.06
    cheon
    -0.06
    POSITIVE LOGITS
    에
    0.07
    .How
    0.07
    _jet
    0.07
     way
    0.07
     ISBN
    0.06
     order
    0.06
    ++){
    0.06
     stopped
    0.06
     appro
    0.06
    ']);
    0.06
    Act Density 0.010%

    No Known Activations