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

    Neuronpedia

    INDEX
    Explanations

    local hosts and kitchens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mainstream
    0.40
    franch
    0.40
     franchises
    0.40
    hotels
    0.39
     disagree
    0.39
     congested
    0.38
     dissenting
    0.38
     crowded
    0.37
     defendant
    0.37
    讽
    0.37
    POSITIVE LOGITS
     Hosts
    1.13
     hosts
    1.09
    Hosts
    1.08
     host
    0.94
     хозя
    0.90
     homemade
    0.89
    hosts
    0.89
     Gastgeber
    0.88
     Host
    0.82
     kitchen
    0.82
    Act Density 0.004%

    No Known Activations