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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash

    This neuron does not activate on any text in the provided examples—i.e. it appears to be effectively inactive.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    เภ
    -0.07
     sage
    -0.06
     London
    -0.06
     pray
    -0.06
     bec
    -0.06
     probes
    -0.06
     possessions
    -0.06
     Plains
    -0.06
    ambique
    -0.06
     readers
    -0.06
    POSITIVE LOGITS
     Hidden
    0.07
     Detected
    0.06
    istingu
    0.06
    直接
    0.06
    ju
    0.06
    _nom
    0.06
    修改
    0.06
    .gridx
    0.06
    role
    0.06
    /ic
    0.06
    Act Density 0.014%

    No Known Activations