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

    Neuronpedia

    INDEX
    Explanations

    software configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     robotic
    -0.07
    composition
    -0.06
     zen
    -0.06
     Organ
    -0.06
     fö
    -0.06
     abstraction
    -0.06
     verdiği
    -0.06
     auss
    -0.06
     rituals
    -0.06
     schemas
    -0.06
    POSITIVE LOGITS
    jmu
    0.06
    MethodName
    0.06
    .order
    0.06
    ฤด
    0.06
     Curl
    0.06
    .Feature
    0.06
    eresa
    0.06
    ForSegue
    0.06
     Rochester
    0.06
     Eaton
    0.06
    Act Density 0.000%

    No Known Activations