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

    Neuronpedia

    INDEX
    Explanations

    percent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     moment
    -0.07
     boils
    -0.07
     готов
    -0.07
     Saf
    -0.07
    ці
    -0.07
    verified
    -0.07
    .party
    -0.06
     selectedItem
    -0.06
    moment
    -0.06
    .delta
    -0.06
    POSITIVE LOGITS
     коштів
    0.06
    (use
    0.06
     позвол
    0.06
    formation
    0.06
     MISSING
    0.06
     src
    0.06
     ARP
    0.06
     connectors
    0.06
     Processor
    0.06
     pym
    0.06
    Act Density 0.073%

    No Known Activations