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

    Neuronpedia

    INDEX
    Explanations

    inflatable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    君
    -0.07
     auc
    -0.07
     patriarch
    -0.07
    .dao
    -0.07
     hastalık
    -0.06
     піз
    -0.06
     apost
    -0.06
    orů
    -0.06
     Languages
    -0.06
    ί
    -0.06
    POSITIVE LOGITS
     inflatable
    0.11
    ],[-
    0.07
    .nt
    0.06
     Throwable
    0.06
    Start
    0.06
    |[
    0.06
     infrastructure
    0.06
    .\
    0.06
     outgoing
    0.06
    +[
    0.06
    Act Density 0.001%

    No Known Activations