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

    Neuronpedia

    INDEX
    Explanations

    memorization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    よび
    -0.06
     conectar
    -0.06
     quest
    -0.06
    .vec
    -0.06
    料理
    -0.06
    argon
    -0.06
    DER
    -0.06
     concussion
    -0.06
    Blend
    -0.06
     Deutschland
    -0.06
    POSITIVE LOGITS
     confront
    0.07
    Intent
    0.06
     memorable
    0.06
    ující
    0.06
    _formats
    0.06
     useCallback
    0.06
     pokemon
    0.06
    John
    0.06
    macro
    0.06
     boredom
    0.06
    Act Density 0.218%

    No Known Activations