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

    Neuronpedia

    INDEX
    Explanations

    every each

    np_max-act · gemini-2.0-flash

    This neuron never activates—it does not detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Dover
    -0.07
     Infantry
    -0.06
     الخاصة
    -0.06
    Solo
    -0.06
    rama
    -0.06
    _interest
    -0.06
     travel
    -0.06
    Absolute
    -0.06
     為
    -0.06
    Retention
    -0.06
    POSITIVE LOGITS
    305
    0.07
    .WebServlet
    0.06
     between
    0.06
     ser
    0.06
    ','=','
    0.06
     zru
    0.06
     huz
    0.06
    ホ
    0.06
     był
    0.06
    木
    0.06
    Act Density 0.011%

    No Known Activations