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

    Neuronpedia

    INDEX
    Explanations

    costs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     эти
    -0.07
    믕
    -0.07
    ductive
    -0.07
    north
    -0.07
    纵
    -0.07
     detect
    -0.07
    леж
    -0.06
    puty
    -0.06
     IonicModule
    -0.06
    .ts
    -0.06
    POSITIVE LOGITS
     Personally
    0.07
     Wal
    0.07
    ."'";↵
    0.07
    ahren
    0.07
    琳
    0.07
     substantially
    0.07
     breweries
    0.06
    工业化
    0.06
    印
    0.06
     bureaucracy
    0.06
    Act Density 0.001%

    No Known Activations