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

    Neuronpedia

    INDEX
    Explanations

    Formula

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    276
    -0.08
     Languages
    -0.07
    782
    -0.07
     เก
    -0.07
     AN
    -0.07
     Participation
    -0.07
     Baxter
    -0.06
    273
    -0.06
     russe
    -0.06
     Jennings
    -0.06
    POSITIVE LOGITS
     Formula
    0.08
     turb
    0.06
    rvé
    0.06
    .Payload
    0.06
    .Filter
    0.06
     formula
    0.06
    dın
    0.06
     latency
    0.06
     ejaculation
    0.06
     сум
    0.06
    Act Density 0.001%

    No Known Activations