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

    Neuronpedia

    INDEX
    Explanations

    rights

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ware
    -0.07
     Write
    -0.07
     complain
    -0.06
     LEFT
    -0.06
     Clone
    -0.06
    まれ
    -0.06
    Captain
    -0.06
    Breaking
    -0.06
     escape
    -0.06
    oksen
    -0.06
    POSITIVE LOGITS
    ._
    0.07
    ่ละ
    0.06
    #[
    0.06
    _transport
    0.06
    (Collectors
    0.06
     inconsistency
    0.06
     ترکی
    0.06
     superiority
    0.06
    (Dialog
    0.06
    NGC
    0.06
    Act Density 0.011%

    No Known Activations